Search | arXiv e-print repository

<!DOCTYPE html> <html lang="en"> <head> <meta charset="utf-8"/> <meta name="viewport" content="width=device-width, initial-scale=1"/>  <link rel="apple-touch-icon" sizes="180x180" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/apple-touch-icon.png"> <link rel="icon" type="image/png" sizes="32x32" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/favicon-32x32.png"> <link rel="icon" type="image/png" sizes="16x16" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/favicon-16x16.png"> <link rel="manifest" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/site.webmanifest"> <link rel="mask-icon" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/safari-pinned-tab.svg" color="#b31b1b"> <link rel="shortcut icon" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/favicon.ico"> <meta name="msapplication-TileColor" content="#b31b1b"> <meta name="msapplication-config" content="images/icons/browserconfig.xml"> <meta name="theme-color" content="#b31b1b">  <title>Search | arXiv e-print repository</title> <script defer src="https://static.arxiv.org/static/base/1.0.0a5/fontawesome-free-5.11.2-web/js/all.js"></script> <link rel="stylesheet" href="https://static.arxiv.org/static/base/1.0.0a5/css/arxivstyle.css" /> <script type="text/x-mathjax-config"> MathJax.Hub.Config({ messageStyle: "none", extensions: ["tex2jax.js"], jax: ["input/TeX", "output/HTML-CSS"], tex2jax: { inlineMath: [ ['$','$'], ["\$","\$"] ], displayMath: [ ['$$','$$'], ["\\[","\\]"] ], processEscapes: true, ignoreClass: '.*', processClass: 'mathjax.*' }, TeX: { extensions: ["AMSmath.js", "AMSsymbols.js", "noErrors.js"], noErrors: { inlineDelimiters: ["$","$"], multiLine: false, style: { "font-size": "normal", "border": "" } } }, "HTML-CSS": { availableFonts: ["TeX"] } }); </script> <script src='//static.arxiv.org/MathJax-2.7.3/MathJax.js'></script> <script src="https://static.arxiv.org/static/base/1.0.0a5/js/notification.js"></script> <link rel="stylesheet" href="https://static.arxiv.org/static/search/0.5.6/css/bulma-tooltip.min.css" /> <link rel="stylesheet" href="https://static.arxiv.org/static/search/0.5.6/css/search.css" /> <script src="https://code.jquery.com/jquery-3.2.1.slim.min.js" integrity="sha256-k2WSCIexGzOj3Euiig+TlR8gA0EmPjuc79OEeY5L45g=" crossorigin="anonymous"></script> <script src="https://static.arxiv.org/static/search/0.5.6/js/fieldset.js"></script> <style> radio#cf-customfield_11400 { display: none; } </style> </head> <body> <header><a href="#main-container" class="is-sr-only">Skip to main content</a>  <div class="attribution level is-marginless" role="banner"> <div class="level-left"> <a class="level-item" href="https://cornell.edu/"><img src="https://static.arxiv.org/static/base/1.0.0a5/images/cornell-reduced-white-SMALL.svg" alt="Cornell University" width="200" aria-label="logo" /></a> </div> <div class="level-right is-marginless"><p class="sponsors level-item is-marginless"><span id="support-ack-url">We gratefully acknowledge support from<br /> the Simons Foundation, <a href="https://info.arxiv.org/about/ourmembers.html">member institutions</a>, and all contributors. <a href="https://info.arxiv.org/about/donate.html">Donate</a></span></p></div> </div>  <div class="identity level is-marginless"> <div class="level-left"> <div class="level-item"> <a class="arxiv" href="https://arxiv.org/" aria-label="arxiv-logo"> <img src="https://static.arxiv.org/static/base/1.0.0a5/images/arxiv-logo-one-color-white.svg" aria-label="logo" alt="arxiv logo" width="85" style="width:85px;"/> </a> </div> </div> <div class="search-block level-right"> <form class="level-item mini-search" method="GET" action="https://arxiv.org/search"> <div class="field has-addons"> <div class="control"> <input class="input is-small" type="text" name="query" placeholder="Search..." aria-label="Search term or terms" /> <p class="help"><a href="https://info.arxiv.org/help">Help</a> | <a href="https://arxiv.org/search/advanced">Advanced Search</a></p> </div> <div class="control"> <div class="select is-small"> <select name="searchtype" aria-label="Field to search"> <option value="all" selected="selected">All fields</option> <option value="title">Title</option> <option value="author">Author</option> <option value="abstract">Abstract</option> <option value="comments">Comments</option> <option value="journal_ref">Journal reference</option> <option value="acm_class">ACM classification</option> <option value="msc_class">MSC classification</option> <option value="report_num">Report number</option> <option value="paper_id">arXiv identifier</option> <option value="doi">DOI</option> <option value="orcid">ORCID</option> <option value="author_id">arXiv author ID</option> <option value="help">Help pages</option> <option value="full_text">Full text</option> </select> </div> </div> <input type="hidden" name="source" value="header"> <button class="button is-small is-cul-darker">Search</button> </div> </form> </div> </div>  <div class="container"> <div class="user-tools is-size-7 has-text-right has-text-weight-bold" role="navigation" aria-label="User menu"> <a href="https://arxiv.org/login">Login</a> </div> </div> </header> <main class="container" id="main-container"> <div class="level is-marginless"> <div class="level-left"> <h1 class="title is-clearfix"> Showing 1–50 of 106 results for author: <span class="mathjax">Rossi, R A</span> </h1> </div> <div class="level-right is-hidden-mobile">  <span class="help" style="display: inline-block;"><a href="https://github.com/arXiv/arxiv-search/releases">Search v0.5.6 released 2020-02-24</a>  </span> </div> </div> <div class="content"> <form method="GET" action="/search/cs" aria-role="search"> Searching in archive <strong>cs</strong>. <a href="/search/?searchtype=author&query=Rossi%2C+R+A">Search in all archives.</a> <div class="field has-addons-tablet"> <div class="control is-expanded"> <label for="query" class="hidden-label">Search term or terms</label> <input class="input is-medium" id="query" name="query" placeholder="Search term..." type="text" value="Rossi, R A"> </div> <div class="select control is-medium"> <label class="is-hidden" for="searchtype">Field</label> <select class="is-medium" id="searchtype" name="searchtype"><option value="all">All fields</option><option value="title">Title</option><option selected value="author">Author(s)</option><option value="abstract">Abstract</option><option value="comments">Comments</option><option value="journal_ref">Journal reference</option><option value="acm_class">ACM classification</option><option value="msc_class">MSC classification</option><option value="report_num">Report number</option><option value="paper_id">arXiv identifier</option><option value="doi">DOI</option><option value="orcid">ORCID</option><option value="license">License (URI)</option><option value="author_id">arXiv author ID</option><option value="help">Help pages</option><option value="full_text">Full text</option></select> </div> <div class="control"> <button class="button is-link is-medium">Search</button> </div> </div> <div class="field"> <div class="control is-size-7"> <label class="radio"> <input checked id="abstracts-0" name="abstracts" type="radio" value="show"> Show abstracts </label> <label class="radio"> <input id="abstracts-1" name="abstracts" type="radio" value="hide"> Hide abstracts </label> </div> </div> <div class="is-clearfix" style="height: 2.5em"> <div class="is-pulled-right"> <a href="/search/advanced?terms-0-term=Rossi%2C+R+A&terms-0-field=author&size=50&order=-announced_date_first">Advanced Search</a> </div> </div> <input type="hidden" name="order" value="-announced_date_first"> <input type="hidden" name="size" value="50"> </form> <div class="level breathe-horizontal"> <div class="level-left"> <form method="GET" action="/search/"> <div style="display: none;"> <select id="searchtype" name="searchtype"><option value="all">All fields</option><option value="title">Title</option><option selected value="author">Author(s)</option><option value="abstract">Abstract</option><option value="comments">Comments</option><option value="journal_ref">Journal reference</option><option value="acm_class">ACM classification</option><option value="msc_class">MSC classification</option><option value="report_num">Report number</option><option value="paper_id">arXiv identifier</option><option value="doi">DOI</option><option value="orcid">ORCID</option><option value="license">License (URI)</option><option value="author_id">arXiv author ID</option><option value="help">Help pages</option><option value="full_text">Full text</option></select> <input id="query" name="query" type="text" value="Rossi, R A"> <ul id="abstracts"><li><input checked id="abstracts-0" name="abstracts" type="radio" value="show"> <label for="abstracts-0">Show abstracts</label></li><li><input id="abstracts-1" name="abstracts" type="radio" value="hide"> <label for="abstracts-1">Hide abstracts</label></li></ul> </div> <div class="box field is-grouped is-grouped-multiline level-item"> <div class="control"> <span class="select is-small"> <select id="size" name="size"><option value="25">25</option><option selected value="50">50</option><option value="100">100</option><option value="200">200</option></select> </span> <label for="size">results per page</label>. </div> <div class="control"> <label for="order">Sort results by</label> <span class="select is-small"> <select id="order" name="order"><option selected value="-announced_date_first">Announcement date (newest first)</option><option value="announced_date_first">Announcement date (oldest first)</option><option value="-submitted_date">Submission date (newest first)</option><option value="submitted_date">Submission date (oldest first)</option><option value="">Relevance</option></select> </span> </div> <div class="control"> <button class="button is-small is-link">Go</button> </div> </div> </form> </div> </div> <nav class="pagination is-small is-centered breathe-horizontal" role="navigation" aria-label="pagination"> <a href="" class="pagination-previous is-invisible">Previous </a> <a href="/search/?searchtype=author&query=Rossi%2C+R+A&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Rossi%2C+R+A&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Rossi%2C+R+A&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </a> </li> <li> <a href="/search/?searchtype=author&query=Rossi%2C+R+A&start=100" class="pagination-link " aria-label="Page 3" aria-current="page">3 </a> </li> </ul> </nav> <ol class="breathe-horizontal" start="1"> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2502.11767">arXiv:2502.11767</a> <span> [<a href="https://arxiv.org/pdf/2502.11767">pdf</a>, <a href="https://arxiv.org/format/2502.11767">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> From Selection to Generation: A Survey of LLM-based Active Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Xia%2C+Y">Yu Xia</a>, <a href="/search/cs?searchtype=author&query=Mukherjee%2C+S">Subhojyoti Mukherjee</a>, <a href="/search/cs?searchtype=author&query=Xie%2C+Z">Zhouhang Xie</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+J">Junda Wu</a>, <a href="/search/cs?searchtype=author&query=Li%2C+X">Xintong Li</a>, <a href="/search/cs?searchtype=author&query=Aponte%2C+R">Ryan Aponte</a>, <a href="/search/cs?searchtype=author&query=Lyu%2C+H">Hanjia Lyu</a>, <a href="/search/cs?searchtype=author&query=Barrow%2C+J">Joe Barrow</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+H">Hongjie Chen</a>, <a href="/search/cs?searchtype=author&query=Dernoncourt%2C+F">Franck Dernoncourt</a>, <a href="/search/cs?searchtype=author&query=Kveton%2C+B">Branislav Kveton</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+T">Tong Yu</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+R">Ruiyi Zhang</a>, <a href="/search/cs?searchtype=author&query=Gu%2C+J">Jiuxiang Gu</a>, <a href="/search/cs?searchtype=author&query=Ahmed%2C+N+K">Nesreen K. Ahmed</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yu Wang</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+X">Xiang Chen</a>, <a href="/search/cs?searchtype=author&query=Deilamsalehy%2C+H">Hanieh Deilamsalehy</a>, <a href="/search/cs?searchtype=author&query=Kim%2C+S">Sungchul Kim</a>, <a href="/search/cs?searchtype=author&query=Hu%2C+Z">Zhengmian Hu</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+Y">Yue Zhao</a>, <a href="/search/cs?searchtype=author&query=Lipka%2C+N">Nedim Lipka</a>, <a href="/search/cs?searchtype=author&query=Yoon%2C+S">Seunghyun Yoon</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+T+K">Ting-Hao Kenneth Huang</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Z">Zichao Wang</a> , et al. (9 additional authors not shown) </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2502.11767v1-abstract-short" style="display: inline;"> Active Learning (AL) has been a powerful paradigm for improving model efficiency and performance by selecting the most informative data points for labeling and training. In recent active learning frameworks, Large Language Models (LLMs) have been employed not only for selection but also for generating entirely new data instances and providing more cost-effective annotations. Motivated by the incre… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.11767v1-abstract-full').style.display = 'inline'; document.getElementById('2502.11767v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.11767v1-abstract-full" style="display: none;"> Active Learning (AL) has been a powerful paradigm for improving model efficiency and performance by selecting the most informative data points for labeling and training. In recent active learning frameworks, Large Language Models (LLMs) have been employed not only for selection but also for generating entirely new data instances and providing more cost-effective annotations. Motivated by the increasing importance of high-quality data and efficient model training in the era of LLMs, we present a comprehensive survey on LLM-based Active Learning. We introduce an intuitive taxonomy that categorizes these techniques and discuss the transformative roles LLMs can play in the active learning loop. We further examine the impact of AL on LLM learning paradigms and its applications across various domains. Finally, we identify open challenges and propose future research directions. This survey aims to serve as an up-to-date resource for researchers and practitioners seeking to gain an intuitive understanding of LLM-based AL techniques and deploy them to new applications. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.11767v1-abstract-full').style.display = 'none'; document.getElementById('2502.11767v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 17 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2502.11740">arXiv:2502.11740</a> <span> [<a href="https://arxiv.org/pdf/2502.11740">pdf</a>, <a href="https://arxiv.org/format/2502.11740">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Mitigating Visual Knowledge Forgetting in MLLM Instruction-tuning via Modality-decoupled Gradient Descent </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wu%2C+J">Junda Wu</a>, <a href="/search/cs?searchtype=author&query=Xiong%2C+Y">Yuxin Xiong</a>, <a href="/search/cs?searchtype=author&query=Li%2C+X">Xintong Li</a>, <a href="/search/cs?searchtype=author&query=Xia%2C+Y">Yu Xia</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+R">Ruoyu Wang</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yu Wang</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+T">Tong Yu</a>, <a href="/search/cs?searchtype=author&query=Kim%2C+S">Sungchul Kim</a>, <a href="/search/cs?searchtype=author&query=Rossi%2C+R+A">Ryan A. Rossi</a>, <a href="/search/cs?searchtype=author&query=Yao%2C+L">Lina Yao</a>, <a href="/search/cs?searchtype=author&query=Shang%2C+J">Jingbo Shang</a>, <a href="/search/cs?searchtype=author&query=McAuley%2C+J">Julian McAuley</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2502.11740v1-abstract-short" style="display: inline;"> Recent MLLMs have shown emerging visual understanding and reasoning abilities after being pre-trained on large-scale multimodal datasets. Unlike pre-training, where MLLMs receive rich visual-text alignment, instruction-tuning is often text-driven with weaker visual supervision, leading to the degradation of pre-trained visual understanding and causing visual forgetting. Existing approaches, such a… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.11740v1-abstract-full').style.display = 'inline'; document.getElementById('2502.11740v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.11740v1-abstract-full" style="display: none;"> Recent MLLMs have shown emerging visual understanding and reasoning abilities after being pre-trained on large-scale multimodal datasets. Unlike pre-training, where MLLMs receive rich visual-text alignment, instruction-tuning is often text-driven with weaker visual supervision, leading to the degradation of pre-trained visual understanding and causing visual forgetting. Existing approaches, such as direct fine-tuning and continual learning methods, fail to explicitly address this issue, often compressing visual representations and prioritizing task alignment over visual retention, which further worsens visual forgetting. To overcome this limitation, we introduce a novel perspective leveraging effective rank to quantify the degradation of visual representation richness, interpreting this degradation through the information bottleneck principle as excessive compression that leads to the degradation of crucial pre-trained visual knowledge. Building on this view, we propose a modality-decoupled gradient descent (MDGD) method that regulates gradient updates to maintain the effective rank of visual representations while mitigating the over-compression effects described by the information bottleneck. By explicitly disentangling the optimization of visual understanding from task-specific alignment, MDGD preserves pre-trained visual knowledge while enabling efficient task adaptation. To enable lightweight instruction-tuning, we further develop a memory-efficient fine-tuning approach using gradient masking, which selectively updates a subset of model parameters to enable parameter-efficient fine-tuning (PEFT), reducing computational overhead while preserving rich visual representations. Extensive experiments across various downstream tasks and backbone MLLMs demonstrate that MDGD effectively mitigates visual forgetting from pre-trained tasks while enabling strong adaptation to new tasks. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.11740v1-abstract-full').style.display = 'none'; document.getElementById('2502.11740v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 17 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">9 pages</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2502.05167">arXiv:2502.05167</a> <span> [<a href="https://arxiv.org/pdf/2502.05167">pdf</a>, <a href="https://arxiv.org/format/2502.05167">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> NoLiMa: Long-Context Evaluation Beyond Literal Matching </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Modarressi%2C+A">Ali Modarressi</a>, <a href="/search/cs?searchtype=author&query=Deilamsalehy%2C+H">Hanieh Deilamsalehy</a>, <a href="/search/cs?searchtype=author&query=Dernoncourt%2C+F">Franck Dernoncourt</a>, <a href="/search/cs?searchtype=author&query=Bui%2C+T">Trung Bui</a>, <a href="/search/cs?searchtype=author&query=Rossi%2C+R+A">Ryan A. Rossi</a>, <a href="/search/cs?searchtype=author&query=Yoon%2C+S">Seunghyun Yoon</a>, <a href="/search/cs?searchtype=author&query=Sch%C3%BCtze%2C+H">Hinrich Sch眉tze</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2502.05167v1-abstract-short" style="display: inline;"> Recent large language models (LLMs) support long contexts ranging from 128K to 1M tokens. A popular method for evaluating these capabilities is the needle-in-a-haystack (NIAH) test, which involves retrieving a "needle" (relevant information) from a "haystack" (long irrelevant context). Extensions of this approach include increasing distractors, fact chaining, and in-context reasoning. However, in… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.05167v1-abstract-full').style.display = 'inline'; document.getElementById('2502.05167v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.05167v1-abstract-full" style="display: none;"> Recent large language models (LLMs) support long contexts ranging from 128K to 1M tokens. A popular method for evaluating these capabilities is the needle-in-a-haystack (NIAH) test, which involves retrieving a "needle" (relevant information) from a "haystack" (long irrelevant context). Extensions of this approach include increasing distractors, fact chaining, and in-context reasoning. However, in these benchmarks, models can exploit existing literal matches between the needle and haystack to simplify the task. To address this, we introduce NoLiMa, a benchmark extending NIAH with a carefully designed needle set, where questions and needles have minimal lexical overlap, requiring models to infer latent associations to locate the needle within the haystack. We evaluate 12 popular LLMs that claim to support contexts of at least 128K tokens. While they perform well in short contexts (<1K), performance degrades significantly as context length increases. At 32K, for instance, 10 models drop below 50% of their strong short-length baselines. Even GPT-4o, one of the top-performing exceptions, experiences a reduction from an almost-perfect baseline of 99.3% to 69.7%. Our analysis suggests these declines stem from the increased difficulty the attention mechanism faces in longer contexts when literal matches are absent, making it harder to retrieve relevant information. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.05167v1-abstract-full').style.display = 'none'; document.getElementById('2502.05167v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 7 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2502.03375">arXiv:2502.03375</a> <span> [<a href="https://arxiv.org/pdf/2502.03375">pdf</a>, <a href="https://arxiv.org/format/2502.03375">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Information Retrieval">cs.IR</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1145/3696410.3714697">10.1145/3696410.3714697 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Interactive Visualization Recommendation with Hier-SUCB </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Hu%2C+S">Songwen Hu</a>, <a href="/search/cs?searchtype=author&query=Rossi%2C+R+A">Ryan A. Rossi</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+T">Tong Yu</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+J">Junda Wu</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+H">Handong Zhao</a>, <a href="/search/cs?searchtype=author&query=Kim%2C+S">Sungchul Kim</a>, <a href="/search/cs?searchtype=author&query=Li%2C+S">Shuai Li</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2502.03375v3-abstract-short" style="display: inline;"> Visualization recommendation aims to enable rapid visual analysis of massive datasets. In real-world scenarios, it is essential to quickly gather and comprehend user preferences to cover users from diverse backgrounds, including varying skill levels and analytical tasks. Previous approaches to personalized visualization recommendations are non-interactive and rely on initial user data for new user… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.03375v3-abstract-full').style.display = 'inline'; document.getElementById('2502.03375v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.03375v3-abstract-full" style="display: none;"> Visualization recommendation aims to enable rapid visual analysis of massive datasets. In real-world scenarios, it is essential to quickly gather and comprehend user preferences to cover users from diverse backgrounds, including varying skill levels and analytical tasks. Previous approaches to personalized visualization recommendations are non-interactive and rely on initial user data for new users. As a result, these models cannot effectively explore options or adapt to real-time feedback. To address this limitation, we propose an interactive personalized visualization recommendation (PVisRec) system that learns on user feedback from previous interactions. For more interactive and accurate recommendations, we propose Hier-SUCB, a contextual combinatorial semi-bandit in the PVisRec setting. Theoretically, we show an improved overall regret bound with the same rank of time but an improved rank of action space. We further demonstrate the effectiveness of Hier-SUCB through extensive experiments where it is comparable to offline methods and outperforms other bandit algorithms in the setting of visualization recommendation. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.03375v3-abstract-full').style.display = 'none'; document.getElementById('2502.03375v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 12 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 5 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2501.06317">arXiv:2501.06317</a> <span> [<a href="https://arxiv.org/pdf/2501.06317">pdf</a>, <a href="https://arxiv.org/format/2501.06317">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Human-Computer Interaction">cs.HC</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> Understanding How Paper Writers Use AI-Generated Captions in Figure Caption Writing </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Yin%2C+H">Ho Yin</a>, <a href="/search/cs?searchtype=author&query=Ng"> Ng</a>, <a href="/search/cs?searchtype=author&query=Hsu%2C+T">Ting-Yao Hsu</a>, <a href="/search/cs?searchtype=author&query=Min%2C+J">Jiyoo Min</a>, <a href="/search/cs?searchtype=author&query=Kim%2C+S">Sungchul Kim</a>, <a href="/search/cs?searchtype=author&query=Rossi%2C+R+A">Ryan A. Rossi</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+T">Tong Yu</a>, <a href="/search/cs?searchtype=author&query=Jung%2C+H">Hyunggu Jung</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+T+%27">Ting-Hao 'Kenneth' Huang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2501.06317v1-abstract-short" style="display: inline;"> Figures and their captions play a key role in scientific publications. However, despite their importance, many captions in published papers are poorly crafted, largely due to a lack of attention by paper authors. While prior AI research has explored caption generation, it has mainly focused on reader-centered use cases, where users evaluate generated captions rather than actively integrating them… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.06317v1-abstract-full').style.display = 'inline'; document.getElementById('2501.06317v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.06317v1-abstract-full" style="display: none;"> Figures and their captions play a key role in scientific publications. However, despite their importance, many captions in published papers are poorly crafted, largely due to a lack of attention by paper authors. While prior AI research has explored caption generation, it has mainly focused on reader-centered use cases, where users evaluate generated captions rather than actively integrating them into their writing. This paper addresses this gap by investigating how paper authors incorporate AI-generated captions into their writing process through a user study involving 18 participants. Each participant rewrote captions for two figures from their own recently published work, using captions generated by state-of-the-art AI models as a resource. By analyzing video recordings of the writing process through interaction analysis, we observed that participants often began by copying and refining AI-generated captions. Paper writers favored longer, detail-rich captions that integrated textual and visual elements but found current AI models less effective for complex figures. These findings highlight the nuanced and diverse nature of figure caption composition, revealing design opportunities for AI systems to better support the challenges of academic writing. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.06317v1-abstract-full').style.display = 'none'; document.getElementById('2501.06317v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 10 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2025. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">This paper will appear at AAAI 2025 Workshop (2nd AI4Research Workshop: Towards a Knowledge-grounded Scientific Research Lifecycle)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2501.02157">arXiv:2501.02157</a> <span> [<a href="https://arxiv.org/pdf/2501.02157">pdf</a>, <a href="https://arxiv.org/format/2501.02157">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> Personalized Graph-Based Retrieval for Large Language Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Au%2C+S">Steven Au</a>, <a href="/search/cs?searchtype=author&query=Dimacali%2C+C+J">Cameron J. Dimacali</a>, <a href="/search/cs?searchtype=author&query=Pedirappagari%2C+O">Ojasmitha Pedirappagari</a>, <a href="/search/cs?searchtype=author&query=Park%2C+N">Namyong Park</a>, <a href="/search/cs?searchtype=author&query=Dernoncourt%2C+F">Franck Dernoncourt</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yu Wang</a>, <a href="/search/cs?searchtype=author&query=Kanakaris%2C+N">Nikos Kanakaris</a>, <a href="/search/cs?searchtype=author&query=Deilamsalehy%2C+H">Hanieh Deilamsalehy</a>, <a href="/search/cs?searchtype=author&query=Rossi%2C+R+A">Ryan A. Rossi</a>, <a href="/search/cs?searchtype=author&query=Ahmed%2C+N+K">Nesreen K. Ahmed</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2501.02157v1-abstract-short" style="display: inline;"> As large language models (LLMs) evolve, their ability to deliver personalized and context-aware responses offers transformative potential for improving user experiences. Existing personalization approaches, however, often rely solely on user history to augment the prompt, limiting their effectiveness in generating tailored outputs, especially in cold-start scenarios with sparse data. To address th… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.02157v1-abstract-full').style.display = 'inline'; document.getElementById('2501.02157v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.02157v1-abstract-full" style="display: none;"> As large language models (LLMs) evolve, their ability to deliver personalized and context-aware responses offers transformative potential for improving user experiences. Existing personalization approaches, however, often rely solely on user history to augment the prompt, limiting their effectiveness in generating tailored outputs, especially in cold-start scenarios with sparse data. To address these limitations, we propose Personalized Graph-based Retrieval-Augmented Generation (PGraphRAG), a framework that leverages user-centric knowledge graphs to enrich personalization. By directly integrating structured user knowledge into the retrieval process and augmenting prompts with user-relevant context, PGraphRAG enhances contextual understanding and output quality. We also introduce the Personalized Graph-based Benchmark for Text Generation, designed to evaluate personalized text generation tasks in real-world settings where user history is sparse or unavailable. Experimental results show that PGraphRAG significantly outperforms state-of-the-art personalization methods across diverse tasks, demonstrating the unique advantages of graph-based retrieval for personalization. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.02157v1-abstract-full').style.display = 'none'; document.getElementById('2501.02157v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 3 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2501.00874">arXiv:2501.00874</a> <span> [<a href="https://arxiv.org/pdf/2501.00874">pdf</a>, <a href="https://arxiv.org/format/2501.00874">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Information Retrieval">cs.IR</span> </div> </div> <p class="title is-5 mathjax"> LUSIFER: Language Universal Space Integration for Enhanced Multilingual Embeddings with Large Language Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Man%2C+H">Hieu Man</a>, <a href="/search/cs?searchtype=author&query=Ngo%2C+N+T">Nghia Trung Ngo</a>, <a href="/search/cs?searchtype=author&query=Lai%2C+V+D">Viet Dac Lai</a>, <a href="/search/cs?searchtype=author&query=Rossi%2C+R+A">Ryan A. Rossi</a>, <a href="/search/cs?searchtype=author&query=Dernoncourt%2C+F">Franck Dernoncourt</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+T+H">Thien Huu Nguyen</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2501.00874v1-abstract-short" style="display: inline;"> Recent advancements in large language models (LLMs) based embedding models have established new state-of-the-art benchmarks for text embedding tasks, particularly in dense vector-based retrieval. However, these models predominantly focus on English, leaving multilingual embedding capabilities largely unexplored. To address this limitation, we present LUSIFER, a novel zero-shot approach that adapts… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.00874v1-abstract-full').style.display = 'inline'; document.getElementById('2501.00874v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.00874v1-abstract-full" style="display: none;"> Recent advancements in large language models (LLMs) based embedding models have established new state-of-the-art benchmarks for text embedding tasks, particularly in dense vector-based retrieval. However, these models predominantly focus on English, leaving multilingual embedding capabilities largely unexplored. To address this limitation, we present LUSIFER, a novel zero-shot approach that adapts LLM-based embedding models for multilingual tasks without requiring multilingual supervision. LUSIFER's architecture combines a multilingual encoder, serving as a language-universal learner, with an LLM-based embedding model optimized for embedding-specific tasks. These components are seamlessly integrated through a minimal set of trainable parameters that act as a connector, effectively transferring the multilingual encoder's language understanding capabilities to the specialized embedding model. Additionally, to comprehensively evaluate multilingual embedding performance, we introduce a new benchmark encompassing 5 primary embedding tasks, 123 diverse datasets, and coverage across 14 languages. Extensive experimental results demonstrate that LUSIFER significantly enhances the multilingual performance across various embedding tasks, particularly for medium and low-resource languages, without requiring explicit multilingual training data. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.00874v1-abstract-full').style.display = 'none'; document.getElementById('2501.00874v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 1 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2501.00309">arXiv:2501.00309</a> <span> [<a href="https://arxiv.org/pdf/2501.00309">pdf</a>, <a href="https://arxiv.org/format/2501.00309">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Information Retrieval">cs.IR</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Retrieval-Augmented Generation with Graphs (GraphRAG) </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Han%2C+H">Haoyu Han</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yu Wang</a>, <a href="/search/cs?searchtype=author&query=Shomer%2C+H">Harry Shomer</a>, <a href="/search/cs?searchtype=author&query=Guo%2C+K">Kai Guo</a>, <a href="/search/cs?searchtype=author&query=Ding%2C+J">Jiayuan Ding</a>, <a href="/search/cs?searchtype=author&query=Lei%2C+Y">Yongjia Lei</a>, <a href="/search/cs?searchtype=author&query=Halappanavar%2C+M">Mahantesh Halappanavar</a>, <a href="/search/cs?searchtype=author&query=Rossi%2C+R+A">Ryan A. Rossi</a>, <a href="/search/cs?searchtype=author&query=Mukherjee%2C+S">Subhabrata Mukherjee</a>, <a href="/search/cs?searchtype=author&query=Tang%2C+X">Xianfeng Tang</a>, <a href="/search/cs?searchtype=author&query=He%2C+Q">Qi He</a>, <a href="/search/cs?searchtype=author&query=Hua%2C+Z">Zhigang Hua</a>, <a href="/search/cs?searchtype=author&query=Long%2C+B">Bo Long</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+T">Tong Zhao</a>, <a href="/search/cs?searchtype=author&query=Shah%2C+N">Neil Shah</a>, <a href="/search/cs?searchtype=author&query=Javari%2C+A">Amin Javari</a>, <a href="/search/cs?searchtype=author&query=Xia%2C+Y">Yinglong Xia</a>, <a href="/search/cs?searchtype=author&query=Tang%2C+J">Jiliang Tang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2501.00309v2-abstract-short" style="display: inline;"> Retrieval-augmented generation (RAG) is a powerful technique that enhances downstream task execution by retrieving additional information, such as knowledge, skills, and tools from external sources. Graph, by its intrinsic "nodes connected by edges" nature, encodes massive heterogeneous and relational information, making it a golden resource for RAG in tremendous real-world applications. As a resu… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.00309v2-abstract-full').style.display = 'inline'; document.getElementById('2501.00309v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.00309v2-abstract-full" style="display: none;"> Retrieval-augmented generation (RAG) is a powerful technique that enhances downstream task execution by retrieving additional information, such as knowledge, skills, and tools from external sources. Graph, by its intrinsic "nodes connected by edges" nature, encodes massive heterogeneous and relational information, making it a golden resource for RAG in tremendous real-world applications. As a result, we have recently witnessed increasing attention on equipping RAG with Graph, i.e., GraphRAG. However, unlike conventional RAG, where the retriever, generator, and external data sources can be uniformly designed in the neural-embedding space, the uniqueness of graph-structured data, such as diverse-formatted and domain-specific relational knowledge, poses unique and significant challenges when designing GraphRAG for different domains. Given the broad applicability, the associated design challenges, and the recent surge in GraphRAG, a systematic and up-to-date survey of its key concepts and techniques is urgently desired. Following this motivation, we present a comprehensive and up-to-date survey on GraphRAG. Our survey first proposes a holistic GraphRAG framework by defining its key components, including query processor, retriever, organizer, generator, and data source. Furthermore, recognizing that graphs in different domains exhibit distinct relational patterns and require dedicated designs, we review GraphRAG techniques uniquely tailored to each domain. Finally, we discuss research challenges and brainstorm directions to inspire cross-disciplinary opportunities. Our survey repository is publicly maintained at https://github.com/Graph-RAG/GraphRAG/. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.00309v2-abstract-full').style.display = 'none'; document.getElementById('2501.00309v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 8 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 31 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2412.15487">arXiv:2412.15487</a> <span> [<a href="https://arxiv.org/pdf/2412.15487">pdf</a>, <a href="https://arxiv.org/format/2412.15487">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> Multi-LLM Text Summarization </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Fang%2C+J">Jiangnan Fang</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+C">Cheng-Tse Liu</a>, <a href="/search/cs?searchtype=author&query=Kim%2C+J">Jieun Kim</a>, <a href="/search/cs?searchtype=author&query=Bhedaru%2C+Y">Yash Bhedaru</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+E">Ethan Liu</a>, <a href="/search/cs?searchtype=author&query=Singh%2C+N">Nikhil Singh</a>, <a href="/search/cs?searchtype=author&query=Lipka%2C+N">Nedim Lipka</a>, <a href="/search/cs?searchtype=author&query=Mathur%2C+P">Puneet Mathur</a>, <a href="/search/cs?searchtype=author&query=Ahmed%2C+N+K">Nesreen K. Ahmed</a>, <a href="/search/cs?searchtype=author&query=Dernoncourt%2C+F">Franck Dernoncourt</a>, <a href="/search/cs?searchtype=author&query=Rossi%2C+R+A">Ryan A. Rossi</a>, <a href="/search/cs?searchtype=author&query=Deilamsalehy%2C+H">Hanieh Deilamsalehy</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2412.15487v1-abstract-short" style="display: inline;"> In this work, we propose a Multi-LLM summarization framework, and investigate two different multi-LLM strategies including centralized and decentralized. Our multi-LLM summarization framework has two fundamentally important steps at each round of conversation: generation and evaluation. These steps are different depending on whether our multi-LLM decentralized summarization is used or centralized.… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.15487v1-abstract-full').style.display = 'inline'; document.getElementById('2412.15487v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.15487v1-abstract-full" style="display: none;"> In this work, we propose a Multi-LLM summarization framework, and investigate two different multi-LLM strategies including centralized and decentralized. Our multi-LLM summarization framework has two fundamentally important steps at each round of conversation: generation and evaluation. These steps are different depending on whether our multi-LLM decentralized summarization is used or centralized. In both our multi-LLM decentralized and centralized strategies, we have k different LLMs that generate diverse summaries of the text. However, during evaluation, our multi-LLM centralized summarization approach leverages a single LLM to evaluate the summaries and select the best one whereas k LLMs are used for decentralized multi-LLM summarization. Overall, we find that our multi-LLM summarization approaches significantly outperform the baselines that leverage only a single LLM by up to 3x. These results indicate the effectiveness of multi-LLM approaches for summarization. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.15487v1-abstract-full').style.display = 'none'; document.getElementById('2412.15487v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 19 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2412.13501">arXiv:2412.13501</a> <span> [<a href="https://arxiv.org/pdf/2412.13501">pdf</a>, <a href="https://arxiv.org/format/2412.13501">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Human-Computer Interaction">cs.HC</span> </div> </div> <p class="title is-5 mathjax"> GUI Agents: A Survey </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Nguyen%2C+D">Dang Nguyen</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+J">Jian Chen</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yu Wang</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+G">Gang Wu</a>, <a href="/search/cs?searchtype=author&query=Park%2C+N">Namyong Park</a>, <a href="/search/cs?searchtype=author&query=Hu%2C+Z">Zhengmian Hu</a>, <a href="/search/cs?searchtype=author&query=Lyu%2C+H">Hanjia Lyu</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+J">Junda Wu</a>, <a href="/search/cs?searchtype=author&query=Aponte%2C+R">Ryan Aponte</a>, <a href="/search/cs?searchtype=author&query=Xia%2C+Y">Yu Xia</a>, <a href="/search/cs?searchtype=author&query=Li%2C+X">Xintong Li</a>, <a href="/search/cs?searchtype=author&query=Shi%2C+J">Jing Shi</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+H">Hongjie Chen</a>, <a href="/search/cs?searchtype=author&query=Lai%2C+V+D">Viet Dac Lai</a>, <a href="/search/cs?searchtype=author&query=Xie%2C+Z">Zhouhang Xie</a>, <a href="/search/cs?searchtype=author&query=Kim%2C+S">Sungchul Kim</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+R">Ruiyi Zhang</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+T">Tong Yu</a>, <a href="/search/cs?searchtype=author&query=Tanjim%2C+M">Mehrab Tanjim</a>, <a href="/search/cs?searchtype=author&query=Ahmed%2C+N+K">Nesreen K. Ahmed</a>, <a href="/search/cs?searchtype=author&query=Mathur%2C+P">Puneet Mathur</a>, <a href="/search/cs?searchtype=author&query=Yoon%2C+S">Seunghyun Yoon</a>, <a href="/search/cs?searchtype=author&query=Yao%2C+L">Lina Yao</a>, <a href="/search/cs?searchtype=author&query=Kveton%2C+B">Branislav Kveton</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+T+H">Thien Huu Nguyen</a> , et al. (4 additional authors not shown) </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2412.13501v1-abstract-short" style="display: inline;"> Graphical User Interface (GUI) agents, powered by Large Foundation Models, have emerged as a transformative approach to automating human-computer interaction. These agents autonomously interact with digital systems or software applications via GUIs, emulating human actions such as clicking, typing, and navigating visual elements across diverse platforms. Motivated by the growing interest and funda… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.13501v1-abstract-full').style.display = 'inline'; document.getElementById('2412.13501v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.13501v1-abstract-full" style="display: none;"> Graphical User Interface (GUI) agents, powered by Large Foundation Models, have emerged as a transformative approach to automating human-computer interaction. These agents autonomously interact with digital systems or software applications via GUIs, emulating human actions such as clicking, typing, and navigating visual elements across diverse platforms. Motivated by the growing interest and fundamental importance of GUI agents, we provide a comprehensive survey that categorizes their benchmarks, evaluation metrics, architectures, and training methods. We propose a unified framework that delineates their perception, reasoning, planning, and acting capabilities. Furthermore, we identify important open challenges and discuss key future directions. Finally, this work serves as a basis for practitioners and researchers to gain an intuitive understanding of current progress, techniques, benchmarks, and critical open problems that remain to be addressed. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.13501v1-abstract-full').style.display = 'none'; document.getElementById('2412.13501v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 17 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2412.12441">arXiv:2412.12441</a> <span> [<a href="https://arxiv.org/pdf/2412.12441">pdf</a>, <a href="https://arxiv.org/format/2412.12441">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Numerical Pruning for Efficient Autoregressive Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Shen%2C+X">Xuan Shen</a>, <a href="/search/cs?searchtype=author&query=Song%2C+Z">Zhao Song</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+Y">Yufa Zhou</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+B">Bo Chen</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+J">Jing Liu</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+R">Ruiyi Zhang</a>, <a href="/search/cs?searchtype=author&query=Rossi%2C+R+A">Ryan A. Rossi</a>, <a href="/search/cs?searchtype=author&query=Tan%2C+H">Hao Tan</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+T">Tong Yu</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+X">Xiang Chen</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+Y">Yufan Zhou</a>, <a href="/search/cs?searchtype=author&query=Sun%2C+T">Tong Sun</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+P">Pu Zhao</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yanzhi Wang</a>, <a href="/search/cs?searchtype=author&query=Gu%2C+J">Jiuxiang Gu</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2412.12441v1-abstract-short" style="display: inline;"> Transformers have emerged as the leading architecture in deep learning, proving to be versatile and highly effective across diverse domains beyond language and image processing. However, their impressive performance often incurs high computational costs due to their substantial model size. This paper focuses on compressing decoder-only transformer-based autoregressive models through structural wei… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.12441v1-abstract-full').style.display = 'inline'; document.getElementById('2412.12441v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.12441v1-abstract-full" style="display: none;"> Transformers have emerged as the leading architecture in deep learning, proving to be versatile and highly effective across diverse domains beyond language and image processing. However, their impressive performance often incurs high computational costs due to their substantial model size. This paper focuses on compressing decoder-only transformer-based autoregressive models through structural weight pruning to improve the model efficiency while preserving performance for both language and image generation tasks. Specifically, we propose a training-free pruning method that calculates a numerical score with Newton's method for the Attention and MLP modules, respectively. Besides, we further propose another compensation algorithm to recover the pruned model for better performance. To verify the effectiveness of our method, we provide both theoretical support and extensive experiments. Our experiments show that our method achieves state-of-the-art performance with reduced memory usage and faster generation speeds on GPUs. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.12441v1-abstract-full').style.display = 'none'; document.getElementById('2412.12441v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 16 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted by AAAI 2025</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2412.10704">arXiv:2412.10704</a> <span> [<a href="https://arxiv.org/pdf/2412.10704">pdf</a>, <a href="https://arxiv.org/format/2412.10704">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> VisDoM: Multi-Document QA with Visually Rich Elements Using Multimodal Retrieval-Augmented Generation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Suri%2C+M">Manan Suri</a>, <a href="/search/cs?searchtype=author&query=Mathur%2C+P">Puneet Mathur</a>, <a href="/search/cs?searchtype=author&query=Dernoncourt%2C+F">Franck Dernoncourt</a>, <a href="/search/cs?searchtype=author&query=Goswami%2C+K">Kanika Goswami</a>, <a href="/search/cs?searchtype=author&query=Rossi%2C+R+A">Ryan A. Rossi</a>, <a href="/search/cs?searchtype=author&query=Manocha%2C+D">Dinesh Manocha</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2412.10704v2-abstract-short" style="display: inline;"> Understanding information from a collection of multiple documents, particularly those with visually rich elements, is important for document-grounded question answering. This paper introduces VisDoMBench, the first comprehensive benchmark designed to evaluate QA systems in multi-document settings with rich multimodal content, including tables, charts, and presentation slides. We propose VisDoMRAG,… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.10704v2-abstract-full').style.display = 'inline'; document.getElementById('2412.10704v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.10704v2-abstract-full" style="display: none;"> Understanding information from a collection of multiple documents, particularly those with visually rich elements, is important for document-grounded question answering. This paper introduces VisDoMBench, the first comprehensive benchmark designed to evaluate QA systems in multi-document settings with rich multimodal content, including tables, charts, and presentation slides. We propose VisDoMRAG, a novel multimodal Retrieval Augmented Generation (RAG) approach that simultaneously utilizes visual and textual RAG, combining robust visual retrieval capabilities with sophisticated linguistic reasoning. VisDoMRAG employs a multi-step reasoning process encompassing evidence curation and chain-of-thought reasoning for concurrent textual and visual RAG pipelines. A key novelty of VisDoMRAG is its consistency-constrained modality fusion mechanism, which aligns the reasoning processes across modalities at inference time to produce a coherent final answer. This leads to enhanced accuracy in scenarios where critical information is distributed across modalities and improved answer verifiability through implicit context attribution. Through extensive experiments involving open-source and proprietary large language models, we benchmark state-of-the-art document QA methods on VisDoMBench. Extensive results show that VisDoMRAG outperforms unimodal and long-context LLM baselines for end-to-end multimodal document QA by 12-20%. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.10704v2-abstract-full').style.display = 'none'; document.getElementById('2412.10704v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 11 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 14 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2412.02142">arXiv:2412.02142</a> <span> [<a href="https://arxiv.org/pdf/2412.02142">pdf</a>, <a href="https://arxiv.org/format/2412.02142">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Information Retrieval">cs.IR</span> </div> </div> <p class="title is-5 mathjax"> Personalized Multimodal Large Language Models: A Survey </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wu%2C+J">Junda Wu</a>, <a href="/search/cs?searchtype=author&query=Lyu%2C+H">Hanjia Lyu</a>, <a href="/search/cs?searchtype=author&query=Xia%2C+Y">Yu Xia</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Z">Zhehao Zhang</a>, <a href="/search/cs?searchtype=author&query=Barrow%2C+J">Joe Barrow</a>, <a href="/search/cs?searchtype=author&query=Kumar%2C+I">Ishita Kumar</a>, <a href="/search/cs?searchtype=author&query=Mirtaheri%2C+M">Mehrnoosh Mirtaheri</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+H">Hongjie Chen</a>, <a href="/search/cs?searchtype=author&query=Rossi%2C+R+A">Ryan A. Rossi</a>, <a href="/search/cs?searchtype=author&query=Dernoncourt%2C+F">Franck Dernoncourt</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+T">Tong Yu</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+R">Ruiyi Zhang</a>, <a href="/search/cs?searchtype=author&query=Gu%2C+J">Jiuxiang Gu</a>, <a href="/search/cs?searchtype=author&query=Ahmed%2C+N+K">Nesreen K. Ahmed</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yu Wang</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+X">Xiang Chen</a>, <a href="/search/cs?searchtype=author&query=Deilamsalehy%2C+H">Hanieh Deilamsalehy</a>, <a href="/search/cs?searchtype=author&query=Park%2C+N">Namyong Park</a>, <a href="/search/cs?searchtype=author&query=Kim%2C+S">Sungchul Kim</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+H">Huanrui Yang</a>, <a href="/search/cs?searchtype=author&query=Mitra%2C+S">Subrata Mitra</a>, <a href="/search/cs?searchtype=author&query=Hu%2C+Z">Zhengmian Hu</a>, <a href="/search/cs?searchtype=author&query=Lipka%2C+N">Nedim Lipka</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+D">Dang Nguyen</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+Y">Yue Zhao</a> , et al. (2 additional authors not shown) </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2412.02142v1-abstract-short" style="display: inline;"> Multimodal Large Language Models (MLLMs) have become increasingly important due to their state-of-the-art performance and ability to integrate multiple data modalities, such as text, images, and audio, to perform complex tasks with high accuracy. This paper presents a comprehensive survey on personalized multimodal large language models, focusing on their architecture, training methods, and applic… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.02142v1-abstract-full').style.display = 'inline'; document.getElementById('2412.02142v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.02142v1-abstract-full" style="display: none;"> Multimodal Large Language Models (MLLMs) have become increasingly important due to their state-of-the-art performance and ability to integrate multiple data modalities, such as text, images, and audio, to perform complex tasks with high accuracy. This paper presents a comprehensive survey on personalized multimodal large language models, focusing on their architecture, training methods, and applications. We propose an intuitive taxonomy for categorizing the techniques used to personalize MLLMs to individual users, and discuss the techniques accordingly. Furthermore, we discuss how such techniques can be combined or adapted when appropriate, highlighting their advantages and underlying rationale. We also provide a succinct summary of personalization tasks investigated in existing research, along with the evaluation metrics commonly used. Additionally, we summarize the datasets that are useful for benchmarking personalized MLLMs. Finally, we outline critical open challenges. This survey aims to serve as a valuable resource for researchers and practitioners seeking to understand and advance the development of personalized multimodal large language models. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.02142v1-abstract-full').style.display = 'none'; document.getElementById('2412.02142v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 2 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.01747">arXiv:2411.01747</a> <span> [<a href="https://arxiv.org/pdf/2411.01747">pdf</a>, <a href="https://arxiv.org/format/2411.01747">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> DynaSaur: Large Language Agents Beyond Predefined Actions </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Nguyen%2C+D">Dang Nguyen</a>, <a href="/search/cs?searchtype=author&query=Lai%2C+V+D">Viet Dac Lai</a>, <a href="/search/cs?searchtype=author&query=Yoon%2C+S">Seunghyun Yoon</a>, <a href="/search/cs?searchtype=author&query=Rossi%2C+R+A">Ryan A. Rossi</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+H">Handong Zhao</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+R">Ruiyi Zhang</a>, <a href="/search/cs?searchtype=author&query=Mathur%2C+P">Puneet Mathur</a>, <a href="/search/cs?searchtype=author&query=Lipka%2C+N">Nedim Lipka</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yu Wang</a>, <a href="/search/cs?searchtype=author&query=Bui%2C+T">Trung Bui</a>, <a href="/search/cs?searchtype=author&query=Dernoncourt%2C+F">Franck Dernoncourt</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+T">Tianyi Zhou</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.01747v1-abstract-short" style="display: inline;"> Existing LLM agent systems typically select actions from a fixed and predefined set at every step. While this approach is effective in closed, narrowly-scoped environments, we argue that it presents two major challenges when deploying LLM agents in real-world scenarios: (1) selecting from a fixed set of actions significantly restricts the planning and acting capabilities of LLM agents, and (2) thi… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.01747v1-abstract-full').style.display = 'inline'; document.getElementById('2411.01747v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.01747v1-abstract-full" style="display: none;"> Existing LLM agent systems typically select actions from a fixed and predefined set at every step. While this approach is effective in closed, narrowly-scoped environments, we argue that it presents two major challenges when deploying LLM agents in real-world scenarios: (1) selecting from a fixed set of actions significantly restricts the planning and acting capabilities of LLM agents, and (2) this approach requires substantial human effort to enumerate and implement all possible actions, which becomes impractical in complex environments with a vast number of potential actions. In this work, we propose an LLM agent framework that enables the dynamic creation and composition of actions in an online manner. In this framework, the agent interacts with the environment by generating and executing programs written in a general-purpose programming language at each step. Furthermore, generated actions are accumulated over time for future reuse. Our extensive experiments on the GAIA benchmark demonstrate that this framework offers significantly greater flexibility and outperforms previous methods. Notably, it allows an LLM agent to recover in scenarios where no relevant action exists in the predefined set or when existing actions fail due to unforeseen edge cases. At the time of writing, we hold the top position on the GAIA public leaderboard. Our code can be found in \href{https://github.com/adobe-research/dynasaur}{https://github.com/adobe-research/dynasaur}. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.01747v1-abstract-full').style.display = 'none'; document.getElementById('2411.01747v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 3 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">15 pages, 8 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.01106">arXiv:2411.01106</a> <span> [<a href="https://arxiv.org/pdf/2411.01106">pdf</a>, <a href="https://arxiv.org/format/2411.01106">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> LoRA-Contextualizing Adaptation of Large Multimodal Models for Long Document Understanding </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Chen%2C+J">Jian Chen</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+R">Ruiyi Zhang</a>, <a href="/search/cs?searchtype=author&query=Zhou%2C+Y">Yufan Zhou</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+T">Tong Yu</a>, <a href="/search/cs?searchtype=author&query=Dernoncourt%2C+F">Franck Dernoncourt</a>, <a href="/search/cs?searchtype=author&query=Gu%2C+J">Jiuxiang Gu</a>, <a href="/search/cs?searchtype=author&query=Rossi%2C+R+A">Ryan A. Rossi</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+C">Changyou Chen</a>, <a href="/search/cs?searchtype=author&query=Sun%2C+T">Tong Sun</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.01106v1-abstract-short" style="display: inline;"> Large multimodal models (LMMs) have recently shown great progress in text-rich image understanding, yet they still struggle with complex, multi-page, visually-rich documents. Traditional methods using document parsers for retrieval-augmented generation suffer from performance and efficiency limitations, while directly presenting all pages to LMMs leads to inefficiencies, especially with lengthy do… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.01106v1-abstract-full').style.display = 'inline'; document.getElementById('2411.01106v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.01106v1-abstract-full" style="display: none;"> Large multimodal models (LMMs) have recently shown great progress in text-rich image understanding, yet they still struggle with complex, multi-page, visually-rich documents. Traditional methods using document parsers for retrieval-augmented generation suffer from performance and efficiency limitations, while directly presenting all pages to LMMs leads to inefficiencies, especially with lengthy documents. In this work, we present a novel framework named LoRA-Contextualizing Adaptation of Large multimodal models (LoCAL), which broadens the capabilities of any LMM to support long-document understanding. We demonstrate that LMMs can effectively serve as multimodal retrievers, fetching relevant pages to answer user questions based on these pages. LoCAL is implemented with two specific LMM adapters: one for evidence page retrieval and another for question answering. Empirical results show state-of-the-art performance on public benchmarks, demonstrating the effectiveness of LoCAL. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.01106v1-abstract-full').style.display = 'none'; document.getElementById('2411.01106v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 1 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Currently Under Review</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.00369">arXiv:2411.00369</a> <span> [<a href="https://arxiv.org/pdf/2411.00369">pdf</a>, <a href="https://arxiv.org/format/2411.00369">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> GRS-QA -- Graph Reasoning-Structured Question Answering Dataset </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Pahilajani%2C+A">Anish Pahilajani</a>, <a href="/search/cs?searchtype=author&query=Trivedi%2C+D">Devasha Trivedi</a>, <a href="/search/cs?searchtype=author&query=Shuai%2C+J">Jincen Shuai</a>, <a href="/search/cs?searchtype=author&query=Yone%2C+K+S">Khin S. Yone</a>, <a href="/search/cs?searchtype=author&query=Jain%2C+S+R">Samyak Rajesh Jain</a>, <a href="/search/cs?searchtype=author&query=Park%2C+N">Namyong Park</a>, <a href="/search/cs?searchtype=author&query=Rossi%2C+R+A">Ryan A. Rossi</a>, <a href="/search/cs?searchtype=author&query=Ahmed%2C+N+K">Nesreen K. Ahmed</a>, <a href="/search/cs?searchtype=author&query=Dernoncourt%2C+F">Franck Dernoncourt</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yu Wang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.00369v3-abstract-short" style="display: inline;"> Large Language Models (LLMs) have excelled in multi-hop question-answering (M-QA) due to their advanced reasoning abilities. However, the impact of the inherent reasoning structures on LLM M-QA performance remains unclear, largely due to the absence of QA datasets that provide fine-grained reasoning structures. To address this gap, we introduce the Graph Reasoning-Structured Question Answering Dat… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.00369v3-abstract-full').style.display = 'inline'; document.getElementById('2411.00369v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.00369v3-abstract-full" style="display: none;"> Large Language Models (LLMs) have excelled in multi-hop question-answering (M-QA) due to their advanced reasoning abilities. However, the impact of the inherent reasoning structures on LLM M-QA performance remains unclear, largely due to the absence of QA datasets that provide fine-grained reasoning structures. To address this gap, we introduce the Graph Reasoning-Structured Question Answering Dataset (GRS-QA), which includes both semantic contexts and reasoning structures for QA pairs. Unlike existing M-QA datasets, where different reasoning structures are entangled together, GRS-QA explicitly captures intricate reasoning pathways by constructing reasoning graphs, where nodes represent textual contexts and edges denote logical flows. These reasoning graphs of different structures enable a fine-grained evaluation of LLM reasoning capabilities across various reasoning structures. Our empirical analysis reveals that LLMs perform differently when handling questions with varying reasoning structures. This finding facilitates the exploration of textual structures as compared with semantics. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.00369v3-abstract-full').style.display = 'none'; document.getElementById('2411.00369v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 7 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 1 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">15 pages, 24 figures, 10 tables</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.00027">arXiv:2411.00027</a> <span> [<a href="https://arxiv.org/pdf/2411.00027">pdf</a>, <a href="https://arxiv.org/format/2411.00027">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> Personalization of Large Language Models: A Survey </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhang%2C+Z">Zhehao Zhang</a>, <a href="/search/cs?searchtype=author&query=Rossi%2C+R+A">Ryan A. Rossi</a>, <a href="/search/cs?searchtype=author&query=Kveton%2C+B">Branislav Kveton</a>, <a href="/search/cs?searchtype=author&query=Shao%2C+Y">Yijia Shao</a>, <a href="/search/cs?searchtype=author&query=Yang%2C+D">Diyi Yang</a>, <a href="/search/cs?searchtype=author&query=Zamani%2C+H">Hamed Zamani</a>, <a href="/search/cs?searchtype=author&query=Dernoncourt%2C+F">Franck Dernoncourt</a>, <a href="/search/cs?searchtype=author&query=Barrow%2C+J">Joe Barrow</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+T">Tong Yu</a>, <a href="/search/cs?searchtype=author&query=Kim%2C+S">Sungchul Kim</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+R">Ruiyi Zhang</a>, <a href="/search/cs?searchtype=author&query=Gu%2C+J">Jiuxiang Gu</a>, <a href="/search/cs?searchtype=author&query=Derr%2C+T">Tyler Derr</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+H">Hongjie Chen</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+J">Junda Wu</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+X">Xiang Chen</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Z">Zichao Wang</a>, <a href="/search/cs?searchtype=author&query=Mitra%2C+S">Subrata Mitra</a>, <a href="/search/cs?searchtype=author&query=Lipka%2C+N">Nedim Lipka</a>, <a href="/search/cs?searchtype=author&query=Ahmed%2C+N">Nesreen Ahmed</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yu Wang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.00027v1-abstract-short" style="display: inline;"> Personalization of Large Language Models (LLMs) has recently become increasingly important with a wide range of applications. Despite the importance and recent progress, most existing works on personalized LLMs have focused either entirely on (a) personalized text generation or (b) leveraging LLMs for personalization-related downstream applications, such as recommendation systems. In this work, we… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.00027v1-abstract-full').style.display = 'inline'; document.getElementById('2411.00027v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.00027v1-abstract-full" style="display: none;"> Personalization of Large Language Models (LLMs) has recently become increasingly important with a wide range of applications. Despite the importance and recent progress, most existing works on personalized LLMs have focused either entirely on (a) personalized text generation or (b) leveraging LLMs for personalization-related downstream applications, such as recommendation systems. In this work, we bridge the gap between these two separate main directions for the first time by introducing a taxonomy for personalized LLM usage and summarizing the key differences and challenges. We provide a formalization of the foundations of personalized LLMs that consolidates and expands notions of personalization of LLMs, defining and discussing novel facets of personalization, usage, and desiderata of personalized LLMs. We then unify the literature across these diverse fields and usage scenarios by proposing systematic taxonomies for the granularity of personalization, personalization techniques, datasets, evaluation methods, and applications of personalized LLMs. Finally, we highlight challenges and important open problems that remain to be addressed. By unifying and surveying recent research using the proposed taxonomies, we aim to provide a clear guide to the existing literature and different facets of personalization in LLMs, empowering both researchers and practitioners. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.00027v1-abstract-full').style.display = 'none'; document.getElementById('2411.00027v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 29 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.22370">arXiv:2410.22370</a> <span> [<a href="https://arxiv.org/pdf/2410.22370">pdf</a>, <a href="https://arxiv.org/format/2410.22370">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Human-Computer Interaction">cs.HC</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Survey of User Interface Design and Interaction Techniques in Generative AI Applications </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Luera%2C+R">Reuben Luera</a>, <a href="/search/cs?searchtype=author&query=Rossi%2C+R+A">Ryan A. Rossi</a>, <a href="/search/cs?searchtype=author&query=Siu%2C+A">Alexa Siu</a>, <a href="/search/cs?searchtype=author&query=Dernoncourt%2C+F">Franck Dernoncourt</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+T">Tong Yu</a>, <a href="/search/cs?searchtype=author&query=Kim%2C+S">Sungchul Kim</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+R">Ruiyi Zhang</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+X">Xiang Chen</a>, <a href="/search/cs?searchtype=author&query=Salehy%2C+H">Hanieh Salehy</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+J">Jian Zhao</a>, <a href="/search/cs?searchtype=author&query=Basu%2C+S">Samyadeep Basu</a>, <a href="/search/cs?searchtype=author&query=Mathur%2C+P">Puneet Mathur</a>, <a href="/search/cs?searchtype=author&query=Lipka%2C+N">Nedim Lipka</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.22370v1-abstract-short" style="display: inline;"> The applications of generative AI have become extremely impressive, and the interplay between users and AI is even more so. Current human-AI interaction literature has taken a broad look at how humans interact with generative AI, but it lacks specificity regarding the user interface designs and patterns used to create these applications. Therefore, we present a survey that comprehensively presents… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.22370v1-abstract-full').style.display = 'inline'; document.getElementById('2410.22370v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.22370v1-abstract-full" style="display: none;"> The applications of generative AI have become extremely impressive, and the interplay between users and AI is even more so. Current human-AI interaction literature has taken a broad look at how humans interact with generative AI, but it lacks specificity regarding the user interface designs and patterns used to create these applications. Therefore, we present a survey that comprehensively presents taxonomies of how a human interacts with AI and the user interaction patterns designed to meet the needs of a variety of relevant use cases. We focus primarily on user-guided interactions, surveying interactions that are initiated by the user and do not include any implicit signals given by the user. With this survey, we aim to create a compendium of different user-interaction patterns that can be used as a reference for designers and developers alike. In doing so, we also strive to lower the entry barrier for those attempting to learn more about the design of generative AI applications. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.22370v1-abstract-full').style.display = 'none'; document.getElementById('2410.22370v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 28 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.20011">arXiv:2410.20011</a> <span> [<a href="https://arxiv.org/pdf/2410.20011">pdf</a>, <a href="https://arxiv.org/format/2410.20011">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> A Survey of Small Language Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Van+Nguyen%2C+C">Chien Van Nguyen</a>, <a href="/search/cs?searchtype=author&query=Shen%2C+X">Xuan Shen</a>, <a href="/search/cs?searchtype=author&query=Aponte%2C+R">Ryan Aponte</a>, <a href="/search/cs?searchtype=author&query=Xia%2C+Y">Yu Xia</a>, <a href="/search/cs?searchtype=author&query=Basu%2C+S">Samyadeep Basu</a>, <a href="/search/cs?searchtype=author&query=Hu%2C+Z">Zhengmian Hu</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+J">Jian Chen</a>, <a href="/search/cs?searchtype=author&query=Parmar%2C+M">Mihir Parmar</a>, <a href="/search/cs?searchtype=author&query=Kunapuli%2C+S">Sasidhar Kunapuli</a>, <a href="/search/cs?searchtype=author&query=Barrow%2C+J">Joe Barrow</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+J">Junda Wu</a>, <a href="/search/cs?searchtype=author&query=Singh%2C+A">Ashish Singh</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yu Wang</a>, <a href="/search/cs?searchtype=author&query=Gu%2C+J">Jiuxiang Gu</a>, <a href="/search/cs?searchtype=author&query=Dernoncourt%2C+F">Franck Dernoncourt</a>, <a href="/search/cs?searchtype=author&query=Ahmed%2C+N+K">Nesreen K. Ahmed</a>, <a href="/search/cs?searchtype=author&query=Lipka%2C+N">Nedim Lipka</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+R">Ruiyi Zhang</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+X">Xiang Chen</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+T">Tong Yu</a>, <a href="/search/cs?searchtype=author&query=Kim%2C+S">Sungchul Kim</a>, <a href="/search/cs?searchtype=author&query=Deilamsalehy%2C+H">Hanieh Deilamsalehy</a>, <a href="/search/cs?searchtype=author&query=Park%2C+N">Namyong Park</a>, <a href="/search/cs?searchtype=author&query=Rimer%2C+M">Mike Rimer</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Z">Zhehao Zhang</a> , et al. (3 additional authors not shown) </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.20011v1-abstract-short" style="display: inline;"> Small Language Models (SLMs) have become increasingly important due to their efficiency and performance to perform various language tasks with minimal computational resources, making them ideal for various settings including on-device, mobile, edge devices, among many others. In this article, we present a comprehensive survey on SLMs, focusing on their architectures, training techniques, and model… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.20011v1-abstract-full').style.display = 'inline'; document.getElementById('2410.20011v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.20011v1-abstract-full" style="display: none;"> Small Language Models (SLMs) have become increasingly important due to their efficiency and performance to perform various language tasks with minimal computational resources, making them ideal for various settings including on-device, mobile, edge devices, among many others. In this article, we present a comprehensive survey on SLMs, focusing on their architectures, training techniques, and model compression techniques. We propose a novel taxonomy for categorizing the methods used to optimize SLMs, including model compression, pruning, and quantization techniques. We summarize the benchmark datasets that are useful for benchmarking SLMs along with the evaluation metrics commonly used. Additionally, we highlight key open challenges that remain to be addressed. Our survey aims to serve as a valuable resource for researchers and practitioners interested in developing and deploying small yet efficient language models. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.20011v1-abstract-full').style.display = 'none'; document.getElementById('2410.20011v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 25 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.18572">arXiv:2410.18572</a> <span> [<a href="https://arxiv.org/pdf/2410.18572">pdf</a>, <a href="https://arxiv.org/format/2410.18572">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Taipan: Efficient and Expressive State Space Language Models with Selective Attention </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Van+Nguyen%2C+C">Chien Van Nguyen</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+H+H">Huy Huu Nguyen</a>, <a href="/search/cs?searchtype=author&query=Pham%2C+T+M">Thang M. Pham</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+R">Ruiyi Zhang</a>, <a href="/search/cs?searchtype=author&query=Deilamsalehy%2C+H">Hanieh Deilamsalehy</a>, <a href="/search/cs?searchtype=author&query=Mathur%2C+P">Puneet Mathur</a>, <a href="/search/cs?searchtype=author&query=Rossi%2C+R+A">Ryan A. Rossi</a>, <a href="/search/cs?searchtype=author&query=Bui%2C+T">Trung Bui</a>, <a href="/search/cs?searchtype=author&query=Lai%2C+V+D">Viet Dac Lai</a>, <a href="/search/cs?searchtype=author&query=Dernoncourt%2C+F">Franck Dernoncourt</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+T+H">Thien Huu Nguyen</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.18572v1-abstract-short" style="display: inline;"> Efficient long-context language modeling remains a significant challenge in Natural Language Processing (NLP). While Transformers dominate language tasks, they struggle with long sequences due to quadratic computational complexity in training and linearly scaling memory costs during inference. Recent State Space Models (SSMs) such as Mamba offer alternatives with constant memory usage, but they un… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.18572v1-abstract-full').style.display = 'inline'; document.getElementById('2410.18572v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.18572v1-abstract-full" style="display: none;"> Efficient long-context language modeling remains a significant challenge in Natural Language Processing (NLP). While Transformers dominate language tasks, they struggle with long sequences due to quadratic computational complexity in training and linearly scaling memory costs during inference. Recent State Space Models (SSMs) such as Mamba offer alternatives with constant memory usage, but they underperform in tasks requiring extensive in-context retrieval. We introduce Taipan, a novel hybrid architecture that combines Mamba-2 with Selective Attention Layers (SALs). These SALs identify tokens requiring long-range interactions, remove less important features, and then augment their representations using the attention module. This approach balances Mamba's efficiency with Transformer-like performance in memory-intensive tasks. By constraining the attention budget, Taipan extends accurate predictions to context lengths of up to 1 million tokens while preserving computational efficiency. Our experiments demonstrate Taipan's superior performance across various scales and tasks, offering a promising solution for efficient long-context language modeling. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.18572v1-abstract-full').style.display = 'none'; document.getElementById('2410.18572v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 24 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.13765">arXiv:2410.13765</a> <span> [<a href="https://arxiv.org/pdf/2410.13765">pdf</a>, <a href="https://arxiv.org/format/2410.13765">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Information Retrieval">cs.IR</span> </div> </div> <p class="title is-5 mathjax"> Knowledge-Aware Query Expansion with Large Language Models for Textual and Relational Retrieval </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Xia%2C+Y">Yu Xia</a>, <a href="/search/cs?searchtype=author&query=Wu%2C+J">Junda Wu</a>, <a href="/search/cs?searchtype=author&query=Kim%2C+S">Sungchul Kim</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+T">Tong Yu</a>, <a href="/search/cs?searchtype=author&query=Rossi%2C+R+A">Ryan A. Rossi</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+H">Haoliang Wang</a>, <a href="/search/cs?searchtype=author&query=McAuley%2C+J">Julian McAuley</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.13765v2-abstract-short" style="display: inline;"> Large language models (LLMs) have been used to generate query expansions augmenting original queries for improving information search. Recent studies also explore providing LLMs with initial retrieval results to generate query expansions more grounded to document corpus. However, these methods mostly focus on enhancing textual similarities between search queries and target documents, overlooking d… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.13765v2-abstract-full').style.display = 'inline'; document.getElementById('2410.13765v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.13765v2-abstract-full" style="display: none;"> Large language models (LLMs) have been used to generate query expansions augmenting original queries for improving information search. Recent studies also explore providing LLMs with initial retrieval results to generate query expansions more grounded to document corpus. However, these methods mostly focus on enhancing textual similarities between search queries and target documents, overlooking document relations. For queries like "Find me a highly rated camera for wildlife photography compatible with my Nikon F-Mount lenses", existing methods may generate expansions that are semantically similar but structurally unrelated to user intents. To handle such semi-structured queries with both textual and relational requirements, in this paper we propose a knowledge-aware query expansion framework, augmenting LLMs with structured document relations from knowledge graph (KG). To further address the limitation of entity-based scoring in existing KG-based methods, we leverage document texts as rich KG node representations and use document-based relation filtering for our Knowledge-Aware Retrieval (KAR). Extensive experiments on three datasets of diverse domains show the advantages of our method compared against state-of-the-art baselines on textual and relational semi-structured retrieval. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.13765v2-abstract-full').style.display = 'none'; document.getElementById('2410.13765v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 5 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 17 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">NAACL 2025</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.15310">arXiv:2409.15310</a> <span> [<a href="https://arxiv.org/pdf/2409.15310">pdf</a>, <a href="https://arxiv.org/format/2409.15310">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> </div> </div> <p class="title is-5 mathjax"> Visual Prompting in Multimodal Large Language Models: A Survey </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wu%2C+J">Junda Wu</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+Z">Zhehao Zhang</a>, <a href="/search/cs?searchtype=author&query=Xia%2C+Y">Yu Xia</a>, <a href="/search/cs?searchtype=author&query=Li%2C+X">Xintong Li</a>, <a href="/search/cs?searchtype=author&query=Xia%2C+Z">Zhaoyang Xia</a>, <a href="/search/cs?searchtype=author&query=Chang%2C+A">Aaron Chang</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+T">Tong Yu</a>, <a href="/search/cs?searchtype=author&query=Kim%2C+S">Sungchul Kim</a>, <a href="/search/cs?searchtype=author&query=Rossi%2C+R+A">Ryan A. Rossi</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+R">Ruiyi Zhang</a>, <a href="/search/cs?searchtype=author&query=Mitra%2C+S">Subrata Mitra</a>, <a href="/search/cs?searchtype=author&query=Metaxas%2C+D+N">Dimitris N. Metaxas</a>, <a href="/search/cs?searchtype=author&query=Yao%2C+L">Lina Yao</a>, <a href="/search/cs?searchtype=author&query=Shang%2C+J">Jingbo Shang</a>, <a href="/search/cs?searchtype=author&query=McAuley%2C+J">Julian McAuley</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2409.15310v1-abstract-short" style="display: inline;"> Multimodal large language models (MLLMs) equip pre-trained large-language models (LLMs) with visual capabilities. While textual prompting in LLMs has been widely studied, visual prompting has emerged for more fine-grained and free-form visual instructions. This paper presents the first comprehensive survey on visual prompting methods in MLLMs, focusing on visual prompting, prompt generation, compo… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.15310v1-abstract-full').style.display = 'inline'; document.getElementById('2409.15310v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.15310v1-abstract-full" style="display: none;"> Multimodal large language models (MLLMs) equip pre-trained large-language models (LLMs) with visual capabilities. While textual prompting in LLMs has been widely studied, visual prompting has emerged for more fine-grained and free-form visual instructions. This paper presents the first comprehensive survey on visual prompting methods in MLLMs, focusing on visual prompting, prompt generation, compositional reasoning, and prompt learning. We categorize existing visual prompts and discuss generative methods for automatic prompt annotations on the images. We also examine visual prompting methods that enable better alignment between visual encoders and backbone LLMs, concerning MLLM's visual grounding, object referring, and compositional reasoning abilities. In addition, we provide a summary of model training and in-context learning methods to improve MLLM's perception and understanding of visual prompts. This paper examines visual prompting methods developed in MLLMs and provides a vision of the future of these methods. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.15310v1-abstract-full').style.display = 'none'; document.getElementById('2409.15310v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 5 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">10 pages</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.13884">arXiv:2409.13884</a> <span> [<a href="https://arxiv.org/pdf/2409.13884">pdf</a>, <a href="https://arxiv.org/format/2409.13884">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computers and Society">cs.CY</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> A Multi-LLM Debiasing Framework </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Owens%2C+D+M">Deonna M. Owens</a>, <a href="/search/cs?searchtype=author&query=Rossi%2C+R+A">Ryan A. Rossi</a>, <a href="/search/cs?searchtype=author&query=Kim%2C+S">Sungchul Kim</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+T">Tong Yu</a>, <a href="/search/cs?searchtype=author&query=Dernoncourt%2C+F">Franck Dernoncourt</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+X">Xiang Chen</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+R">Ruiyi Zhang</a>, <a href="/search/cs?searchtype=author&query=Gu%2C+J">Jiuxiang Gu</a>, <a href="/search/cs?searchtype=author&query=Deilamsalehy%2C+H">Hanieh Deilamsalehy</a>, <a href="/search/cs?searchtype=author&query=Lipka%2C+N">Nedim Lipka</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2409.13884v1-abstract-short" style="display: inline;"> Large Language Models (LLMs) are powerful tools with the potential to benefit society immensely, yet, they have demonstrated biases that perpetuate societal inequalities. Despite significant advancements in bias mitigation techniques using data augmentation, zero-shot prompting, and model fine-tuning, biases continuously persist, including subtle biases that may elude human detection. Recent resea… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.13884v1-abstract-full').style.display = 'inline'; document.getElementById('2409.13884v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.13884v1-abstract-full" style="display: none;"> Large Language Models (LLMs) are powerful tools with the potential to benefit society immensely, yet, they have demonstrated biases that perpetuate societal inequalities. Despite significant advancements in bias mitigation techniques using data augmentation, zero-shot prompting, and model fine-tuning, biases continuously persist, including subtle biases that may elude human detection. Recent research has shown a growing interest in multi-LLM approaches, which have been demonstrated to be effective in improving the quality of reasoning and factuality in LLMs. Building on this approach, we propose a novel multi-LLM debiasing framework aimed at reducing bias in LLMs. Our work is the first to introduce and evaluate two distinct approaches within this framework for debiasing LLMs: a centralized method, where the conversation is facilitated by a single central LLM, and a decentralized method, where all models communicate directly. Our findings reveal that our multi-LLM framework significantly reduces bias in LLMs, outperforming the baseline method across several social groups. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.13884v1-abstract-full').style.display = 'none'; document.getElementById('2409.13884v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 20 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.02361">arXiv:2409.02361</a> <span> [<a href="https://arxiv.org/pdf/2409.02361">pdf</a>, <a href="https://arxiv.org/format/2409.02361">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> Diversify-verify-adapt: Efficient and Robust Retrieval-Augmented Ambiguous Question Answering </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=In%2C+Y">Yeonjun In</a>, <a href="/search/cs?searchtype=author&query=Kim%2C+S">Sungchul Kim</a>, <a href="/search/cs?searchtype=author&query=Rossi%2C+R+A">Ryan A. Rossi</a>, <a href="/search/cs?searchtype=author&query=Tanjim%2C+M+M">Md Mehrab Tanjim</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+T">Tong Yu</a>, <a href="/search/cs?searchtype=author&query=Sinha%2C+R">Ritwik Sinha</a>, <a href="/search/cs?searchtype=author&query=Park%2C+C">Chanyoung Park</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2409.02361v2-abstract-short" style="display: inline;"> The retrieval augmented generation (RAG) framework addresses an ambiguity in user queries in QA systems by retrieving passages that cover all plausible interpretations and generating comprehensive responses based on the passages. However, our preliminary studies reveal that a single retrieval process often suffers from low quality results, as the retrieved passages frequently fail to capture all p… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.02361v2-abstract-full').style.display = 'inline'; document.getElementById('2409.02361v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.02361v2-abstract-full" style="display: none;"> The retrieval augmented generation (RAG) framework addresses an ambiguity in user queries in QA systems by retrieving passages that cover all plausible interpretations and generating comprehensive responses based on the passages. However, our preliminary studies reveal that a single retrieval process often suffers from low quality results, as the retrieved passages frequently fail to capture all plausible interpretations. Although the iterative RAG approach has been proposed to address this problem, it comes at the cost of significantly reduced efficiency. To address these issues, we propose the diversify-verify-adapt (DIVA) framework. DIVA first diversifies the retrieved passages to encompass diverse interpretations. Subsequently, DIVA verifies the quality of the passages and adapts the most suitable approach tailored to their quality. This approach improves the QA systems accuracy and robustness by handling low quality retrieval issue in ambiguous questions, while enhancing efficiency. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.02361v2-abstract-full').style.display = 'none'; document.getElementById('2409.02361v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 6 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 3 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">NAACL 2025 Main</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2408.02861">arXiv:2408.02861</a> <span> [<a href="https://arxiv.org/pdf/2408.02861">pdf</a>, <a href="https://arxiv.org/format/2408.02861">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> A Framework for Fine-Tuning LLMs using Heterogeneous Feedback </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Aponte%2C+R">Ryan Aponte</a>, <a href="/search/cs?searchtype=author&query=Rossi%2C+R+A">Ryan A. Rossi</a>, <a href="/search/cs?searchtype=author&query=Guo%2C+S">Shunan Guo</a>, <a href="/search/cs?searchtype=author&query=Dernoncourt%2C+F">Franck Dernoncourt</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+T">Tong Yu</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+X">Xiang Chen</a>, <a href="/search/cs?searchtype=author&query=Mitra%2C+S">Subrata Mitra</a>, <a href="/search/cs?searchtype=author&query=Lipka%2C+N">Nedim Lipka</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2408.02861v1-abstract-short" style="display: inline;"> Large language models (LLMs) have been applied to a wide range of tasks, including text summarization, web navigation, and chatbots. They have benefitted from supervised fine-tuning (SFT) and reinforcement learning from human feedback (RLHF) following an unsupervised pretraining. These datasets can be difficult to collect, limited in scope, and vary in sample quality. Additionally, datasets can va… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.02861v1-abstract-full').style.display = 'inline'; document.getElementById('2408.02861v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.02861v1-abstract-full" style="display: none;"> Large language models (LLMs) have been applied to a wide range of tasks, including text summarization, web navigation, and chatbots. They have benefitted from supervised fine-tuning (SFT) and reinforcement learning from human feedback (RLHF) following an unsupervised pretraining. These datasets can be difficult to collect, limited in scope, and vary in sample quality. Additionally, datasets can vary extensively in supervision format, from numerical to binary as well as multi-dimensional with many different values. We present a framework for fine-tuning LLMs using heterogeneous feedback, which has two main components. First, we combine the heterogeneous feedback data into a single supervision format, compatible with methods like SFT and RLHF. Next, given this unified feedback dataset, we extract a high-quality and diverse subset to obtain performance increases potentially exceeding the full dataset. We conduct extensive experiments to understand the effectiveness of these techniques for incorporating heterogeneous feedback, and demonstrate improvements from using a high-quality and diverse subset of the data. We find that our framework is able to improve models in multiple areas simultaneously, such as in instruction following and bias reduction. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.02861v1-abstract-full').style.display = 'none'; document.getElementById('2408.02861v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 5 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">7 pages, 1 figure</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">ACM Class:</span> I.2.7 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2407.16073">arXiv:2407.16073</a> <span> [<a href="https://arxiv.org/pdf/2407.16073">pdf</a>, <a href="https://arxiv.org/format/2407.16073">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> KaPQA: Knowledge-Augmented Product Question-Answering </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Eppalapally%2C+S">Swetha Eppalapally</a>, <a href="/search/cs?searchtype=author&query=Dangi%2C+D">Daksh Dangi</a>, <a href="/search/cs?searchtype=author&query=Bhat%2C+C">Chaithra Bhat</a>, <a href="/search/cs?searchtype=author&query=Gupta%2C+A">Ankita Gupta</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+R">Ruiyi Zhang</a>, <a href="/search/cs?searchtype=author&query=Agarwal%2C+S">Shubham Agarwal</a>, <a href="/search/cs?searchtype=author&query=Bagga%2C+K">Karishma Bagga</a>, <a href="/search/cs?searchtype=author&query=Yoon%2C+S">Seunghyun Yoon</a>, <a href="/search/cs?searchtype=author&query=Lipka%2C+N">Nedim Lipka</a>, <a href="/search/cs?searchtype=author&query=Rossi%2C+R+A">Ryan A. Rossi</a>, <a href="/search/cs?searchtype=author&query=Dernoncourt%2C+F">Franck Dernoncourt</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2407.16073v1-abstract-short" style="display: inline;"> Question-answering for domain-specific applications has recently attracted much interest due to the latest advancements in large language models (LLMs). However, accurately assessing the performance of these applications remains a challenge, mainly due to the lack of suitable benchmarks that effectively simulate real-world scenarios. To address this challenge, we introduce two product question-ans… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.16073v1-abstract-full').style.display = 'inline'; document.getElementById('2407.16073v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.16073v1-abstract-full" style="display: none;"> Question-answering for domain-specific applications has recently attracted much interest due to the latest advancements in large language models (LLMs). However, accurately assessing the performance of these applications remains a challenge, mainly due to the lack of suitable benchmarks that effectively simulate real-world scenarios. To address this challenge, we introduce two product question-answering (QA) datasets focused on Adobe Acrobat and Photoshop products to help evaluate the performance of existing models on domain-specific product QA tasks. Additionally, we propose a novel knowledge-driven RAG-QA framework to enhance the performance of the models in the product QA task. Our experiments demonstrated that inducing domain knowledge through query reformulation allowed for increased retrieval and generative performance when compared to standard RAG-QA methods. This improvement, however, is slight, and thus illustrates the challenge posed by the datasets introduced. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.16073v1-abstract-full').style.display = 'none'; document.getElementById('2407.16073v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 22 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted at the ACL 2024 Workshop on Knowledge Augmented Methods for NLP</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2407.11016">arXiv:2407.11016</a> <span> [<a href="https://arxiv.org/pdf/2407.11016">pdf</a>, <a href="https://arxiv.org/format/2407.11016">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> LongLaMP: A Benchmark for Personalized Long-form Text Generation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Kumar%2C+I">Ishita Kumar</a>, <a href="/search/cs?searchtype=author&query=Viswanathan%2C+S">Snigdha Viswanathan</a>, <a href="/search/cs?searchtype=author&query=Yerra%2C+S">Sushrita Yerra</a>, <a href="/search/cs?searchtype=author&query=Salemi%2C+A">Alireza Salemi</a>, <a href="/search/cs?searchtype=author&query=Rossi%2C+R+A">Ryan A. Rossi</a>, <a href="/search/cs?searchtype=author&query=Dernoncourt%2C+F">Franck Dernoncourt</a>, <a href="/search/cs?searchtype=author&query=Deilamsalehy%2C+H">Hanieh Deilamsalehy</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+X">Xiang Chen</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+R">Ruiyi Zhang</a>, <a href="/search/cs?searchtype=author&query=Agarwal%2C+S">Shubham Agarwal</a>, <a href="/search/cs?searchtype=author&query=Lipka%2C+N">Nedim Lipka</a>, <a href="/search/cs?searchtype=author&query=Van+Nguyen%2C+C">Chien Van Nguyen</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+T+H">Thien Huu Nguyen</a>, <a href="/search/cs?searchtype=author&query=Zamani%2C+H">Hamed Zamani</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2407.11016v3-abstract-short" style="display: inline;"> Long-text generation is seemingly ubiquitous in real-world applications of large language models such as generating an email or writing a review. Despite the fundamental importance and prevalence of long-text generation in many practical applications, existing work on personalized generation has focused on the generation of very short text. To overcome these limitations, we study the problem of pe… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.11016v3-abstract-full').style.display = 'inline'; document.getElementById('2407.11016v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.11016v3-abstract-full" style="display: none;"> Long-text generation is seemingly ubiquitous in real-world applications of large language models such as generating an email or writing a review. Despite the fundamental importance and prevalence of long-text generation in many practical applications, existing work on personalized generation has focused on the generation of very short text. To overcome these limitations, we study the problem of personalized long-text generation, that is, generating long-text that is personalized for a specific user while being practically useful for the vast majority of real-world applications that naturally require the generation of longer text. In this work, we demonstrate the importance of user-specific personalization for long-text generation tasks and develop the Long-text Language Model Personalization (LongLaMP) Benchmark. LongLaMP provides a comprehensive and diverse evaluation framework for personalized long-text generation. Extensive experiments on LongLaMP for zero-shot and fine-tuned language tasks demonstrate the effectiveness of the proposed benchmark and its utility for developing and evaluating techniques for personalized long-text generation across a wide variety of long-text generation tasks. The results highlight the importance of personalization across a wide variety of long-text generation tasks. Finally, we release the benchmark for others to use for this important problem. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.11016v3-abstract-full').style.display = 'none'; document.getElementById('2407.11016v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 14 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 26 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2407.07291">arXiv:2407.07291</a> <span> [<a href="https://arxiv.org/pdf/2407.07291">pdf</a>, <a href="https://arxiv.org/format/2407.07291">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</span> </div> </div> <p class="title is-5 mathjax"> Causal Discovery in Semi-Stationary Time Series </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Gao%2C+S">Shanyun Gao</a>, <a href="/search/cs?searchtype=author&query=Addanki%2C+R">Raghavendra Addanki</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+T">Tong Yu</a>, <a href="/search/cs?searchtype=author&query=Rossi%2C+R+A">Ryan A. Rossi</a>, <a href="/search/cs?searchtype=author&query=Kocaoglu%2C+M">Murat Kocaoglu</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2407.07291v1-abstract-short" style="display: inline;"> Discovering causal relations from observational time series without making the stationary assumption is a significant challenge. In practice, this challenge is common in many areas, such as retail sales, transportation systems, and medical science. Here, we consider this problem for a class of non-stationary time series. The structural causal model (SCM) of this type of time series, called the sem… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.07291v1-abstract-full').style.display = 'inline'; document.getElementById('2407.07291v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.07291v1-abstract-full" style="display: none;"> Discovering causal relations from observational time series without making the stationary assumption is a significant challenge. In practice, this challenge is common in many areas, such as retail sales, transportation systems, and medical science. Here, we consider this problem for a class of non-stationary time series. The structural causal model (SCM) of this type of time series, called the semi-stationary time series, exhibits that a finite number of different causal mechanisms occur sequentially and periodically across time. This model holds considerable practical utility because it can represent periodicity, including common occurrences such as seasonality and diurnal variation. We propose a constraint-based, non-parametric algorithm for discovering causal relations in this setting. The resulting algorithm, PCMCI$_惟$, can capture the alternating and recurring changes in the causal mechanisms and then identify the underlying causal graph with conditional independence (CI) tests. We show that this algorithm is sound in identifying causal relations on discrete time series. We validate the algorithm with extensive experiments on continuous and discrete simulated data. We also apply our algorithm to a real-world climate dataset. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.07291v1-abstract-full').style.display = 'none'; document.getElementById('2407.07291v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 9 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">ACM Class:</span> I.2.6, G.3 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2407.07290">arXiv:2407.07290</a> <span> [<a href="https://arxiv.org/pdf/2407.07290">pdf</a>, <a href="https://arxiv.org/format/2407.07290">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</span> </div> </div> <p class="title is-5 mathjax"> Causal Discovery-Driven Change Point Detection in Time Series </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Gao%2C+S">Shanyun Gao</a>, <a href="/search/cs?searchtype=author&query=Addanki%2C+R">Raghavendra Addanki</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+T">Tong Yu</a>, <a href="/search/cs?searchtype=author&query=Rossi%2C+R+A">Ryan A. Rossi</a>, <a href="/search/cs?searchtype=author&query=Kocaoglu%2C+M">Murat Kocaoglu</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2407.07290v1-abstract-short" style="display: inline;"> Change point detection in time series seeks to identify times when the probability distribution of time series changes. It is widely applied in many areas, such as human-activity sensing and medical science. In the context of multivariate time series, this typically involves examining the joint distribution of high-dimensional data: If any one variable changes, the whole time series is assumed to… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.07290v1-abstract-full').style.display = 'inline'; document.getElementById('2407.07290v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.07290v1-abstract-full" style="display: none;"> Change point detection in time series seeks to identify times when the probability distribution of time series changes. It is widely applied in many areas, such as human-activity sensing and medical science. In the context of multivariate time series, this typically involves examining the joint distribution of high-dimensional data: If any one variable changes, the whole time series is assumed to have changed. However, in practical applications, we may be interested only in certain components of the time series, exploring abrupt changes in their distributions in the presence of other time series. Here, assuming an underlying structural causal model that governs the time-series data generation, we address this problem by proposing a two-stage non-parametric algorithm that first learns parts of the causal structure through constraint-based discovery methods. The algorithm then uses conditional relative Pearson divergence estimation to identify the change points. The conditional relative Pearson divergence quantifies the distribution disparity between consecutive segments in the time series, while the causal discovery method enables a focus on the causal mechanism, facilitating access to independent and identically distributed (IID) samples. Theoretically, the typical assumption of samples being IID in conventional change point detection methods can be relaxed based on the Causal Markov Condition. Through experiments on both synthetic and real-world datasets, we validate the correctness and utility of our approach. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.07290v1-abstract-full').style.display = 'none'; document.getElementById('2407.07290v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 9 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">ACM Class:</span> I.2.6, G.3 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2407.04855">arXiv:2407.04855</a> <span> [<a href="https://arxiv.org/pdf/2407.04855">pdf</a>, <a href="https://arxiv.org/format/2407.04855">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Towards Enhancing Coherence in Extractive Summarization: Dataset and Experiments with LLMs </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Parmar%2C+M">Mihir Parmar</a>, <a href="/search/cs?searchtype=author&query=Deilamsalehy%2C+H">Hanieh Deilamsalehy</a>, <a href="/search/cs?searchtype=author&query=Dernoncourt%2C+F">Franck Dernoncourt</a>, <a href="/search/cs?searchtype=author&query=Yoon%2C+S">Seunghyun Yoon</a>, <a href="/search/cs?searchtype=author&query=Rossi%2C+R+A">Ryan A. Rossi</a>, <a href="/search/cs?searchtype=author&query=Bui%2C+T">Trung Bui</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2407.04855v1-abstract-short" style="display: inline;"> Extractive summarization plays a pivotal role in natural language processing due to its wide-range applications in summarizing diverse content efficiently, while also being faithful to the original content. Despite significant advancement achieved in extractive summarization by Large Language Models (LLMs), these summaries frequently exhibit incoherence. An important aspect of the coherent summary… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.04855v1-abstract-full').style.display = 'inline'; document.getElementById('2407.04855v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.04855v1-abstract-full" style="display: none;"> Extractive summarization plays a pivotal role in natural language processing due to its wide-range applications in summarizing diverse content efficiently, while also being faithful to the original content. Despite significant advancement achieved in extractive summarization by Large Language Models (LLMs), these summaries frequently exhibit incoherence. An important aspect of the coherent summary is its readability for intended users. Although there have been many datasets and benchmarks proposed for creating coherent extractive summaries, none of them currently incorporate user intent to improve coherence in extractive summarization. Motivated by this, we propose a systematically created human-annotated dataset consisting of coherent summaries for five publicly available datasets and natural language user feedback, offering valuable insights into how to improve coherence in extractive summaries. We utilize this dataset for aligning LLMs through supervised fine-tuning with natural language human feedback to enhance the coherence of their generated summaries. Preliminary experiments with Falcon-40B and Llama-2-13B show significant performance improvements (~10% Rouge-L) in terms of producing coherent summaries. We further utilize human feedback to benchmark results over instruction-tuned models such as FLAN-T5 which resulted in several interesting findings. Data and source code are available at https://github.com/Mihir3009/Extract-AI. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.04855v1-abstract-full').style.display = 'none'; document.getElementById('2407.04855v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 5 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">10 pages</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2407.02750">arXiv:2407.02750</a> <span> [<a href="https://arxiv.org/pdf/2407.02750">pdf</a>, <a href="https://arxiv.org/format/2407.02750">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> Learning to Reduce: Towards Improving Performance of Large Language Models on Structured Data </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Lee%2C+Y">Younghun Lee</a>, <a href="/search/cs?searchtype=author&query=Kim%2C+S">Sungchul Kim</a>, <a href="/search/cs?searchtype=author&query=Rossi%2C+R+A">Ryan A. Rossi</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+T">Tong Yu</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+X">Xiang Chen</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2407.02750v1-abstract-short" style="display: inline;"> Large Language Models (LLMs) have been achieving competent performance on a wide range of downstream tasks, yet existing work shows that inference on structured data is challenging for LLMs. This is because LLMs need to either understand long structured data or select the most relevant evidence before inference, and both approaches are not trivial. This paper proposes a framework, Learning to Redu… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.02750v1-abstract-full').style.display = 'inline'; document.getElementById('2407.02750v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.02750v1-abstract-full" style="display: none;"> Large Language Models (LLMs) have been achieving competent performance on a wide range of downstream tasks, yet existing work shows that inference on structured data is challenging for LLMs. This is because LLMs need to either understand long structured data or select the most relevant evidence before inference, and both approaches are not trivial. This paper proposes a framework, Learning to Reduce, that fine-tunes a language model with On-Policy Learning to generate a reduced version of an input structured data. When compared to state-of-the-art LLMs like GPT-4, Learning to Reduce not only achieves outstanding performance in reducing the input, but shows generalizability on different datasets. We further show that the model fine-tuned with our framework helps LLMs better perform on table QA tasks especially when the context is longer. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.02750v1-abstract-full').style.display = 'none'; document.getElementById('2407.02750v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 2 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">ICML 2024 Workshop on Long-Context Foundation Models, Vienna, Austria 2024. arXiv admin note: substantial text overlap with arXiv:2402.14195</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2406.05109">arXiv:2406.05109</a> <span> [<a href="https://arxiv.org/pdf/2406.05109">pdf</a>, <a href="https://arxiv.org/format/2406.05109">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Large Generative Graph Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yu Wang</a>, <a href="/search/cs?searchtype=author&query=Rossi%2C+R+A">Ryan A. Rossi</a>, <a href="/search/cs?searchtype=author&query=Park%2C+N">Namyong Park</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+H">Huiyuan Chen</a>, <a href="/search/cs?searchtype=author&query=Ahmed%2C+N+K">Nesreen K. Ahmed</a>, <a href="/search/cs?searchtype=author&query=Trivedi%2C+P">Puja Trivedi</a>, <a href="/search/cs?searchtype=author&query=Dernoncourt%2C+F">Franck Dernoncourt</a>, <a href="/search/cs?searchtype=author&query=Koutra%2C+D">Danai Koutra</a>, <a href="/search/cs?searchtype=author&query=Derr%2C+T">Tyler Derr</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2406.05109v1-abstract-short" style="display: inline;"> Large Generative Models (LGMs) such as GPT, Stable Diffusion, Sora, and Suno are trained on a huge amount of language corpus, images, videos, and audio that are extremely diverse from numerous domains. This training paradigm over diverse well-curated data lies at the heart of generating creative and sensible content. However, all previous graph generative models (e.g., GraphRNN, MDVAE, MoFlow, GDS… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.05109v1-abstract-full').style.display = 'inline'; document.getElementById('2406.05109v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.05109v1-abstract-full" style="display: none;"> Large Generative Models (LGMs) such as GPT, Stable Diffusion, Sora, and Suno are trained on a huge amount of language corpus, images, videos, and audio that are extremely diverse from numerous domains. This training paradigm over diverse well-curated data lies at the heart of generating creative and sensible content. However, all previous graph generative models (e.g., GraphRNN, MDVAE, MoFlow, GDSS, and DiGress) have been trained only on one dataset each time, which cannot replicate the revolutionary success achieved by LGMs in other fields. To remedy this crucial gap, we propose a new class of graph generative model called Large Graph Generative Model (LGGM) that is trained on a large corpus of graphs (over 5000 graphs) from 13 different domains. We empirically demonstrate that the pre-trained LGGM has superior zero-shot generative capability to existing graph generative models. Furthermore, our pre-trained LGGM can be easily fine-tuned with graphs from target domains and demonstrate even better performance than those directly trained from scratch, behaving as a solid starting point for real-world customization. Inspired by Stable Diffusion, we further equip LGGM with the capability to generate graphs given text prompts (Text-to-Graph), such as the description of the network name and domain (i.e., "The power-1138-bus graph represents a network of buses in a power distribution system."), and network statistics (i.e., "The graph has a low average degree, suitable for modeling social media interactions."). This Text-to-Graph capability integrates the extensive world knowledge in the underlying language model, offering users fine-grained control of the generated graphs. We release the code, the model checkpoint, and the datasets at https://lggm-lg.github.io/. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.05109v1-abstract-full').style.display = 'none'; document.getElementById('2406.05109v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 7 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2404.11602">arXiv:2404.11602</a> <span> [<a href="https://arxiv.org/pdf/2404.11602">pdf</a>, <a href="https://arxiv.org/format/2404.11602">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Human-Computer Interaction">cs.HC</span> </div> </div> <p class="title is-5 mathjax"> Interaction Techniques for Exploratory Data Visualization on Mobile Devices </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Snyder%2C+L+S">Luke S. Snyder</a>, <a href="/search/cs?searchtype=author&query=Rossi%2C+R+A">Ryan A. Rossi</a>, <a href="/search/cs?searchtype=author&query=Koh%2C+E">Eunyee Koh</a>, <a href="/search/cs?searchtype=author&query=Heer%2C+J">Jeffrey Heer</a>, <a href="/search/cs?searchtype=author&query=Hoffswell%2C+J">Jane Hoffswell</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2404.11602v1-abstract-short" style="display: inline;"> The ubiquity and on-the-go availability of mobile devices makes them central to many tasks such as interpersonal communication and media consumption. However, despite the potential of mobile devices for on-demand exploratory data visualization, existing mobile interactions are difficult, often using highly custom interactions, complex gestures, or multi-modal input. We synthesize limitations from… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.11602v1-abstract-full').style.display = 'inline'; document.getElementById('2404.11602v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2404.11602v1-abstract-full" style="display: none;"> The ubiquity and on-the-go availability of mobile devices makes them central to many tasks such as interpersonal communication and media consumption. However, despite the potential of mobile devices for on-demand exploratory data visualization, existing mobile interactions are difficult, often using highly custom interactions, complex gestures, or multi-modal input. We synthesize limitations from the literature and outline four motivating principles for improved mobile interaction: leverage ubiquitous modalities, prioritize discoverability, enable rapid in-context data exploration, and promote graceful recovery. We then contribute thirteen interaction candidates and conduct a formative study with twelve participants who experienced our interactions in a testbed prototype. Based on these interviews, we discuss design considerations and tradeoffs from four main themes: precise and rapid inspection, focused navigation, single-touch and fixed orientation interaction, and judicious use of motion. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.11602v1-abstract-full').style.display = 'none'; document.getElementById('2404.11602v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 17 April, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">4 pages, 1 figure, 1 table, EuroVis 2024 Short Papers</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2404.01588">arXiv:2404.01588</a> <span> [<a href="https://arxiv.org/pdf/2404.01588">pdf</a>, <a href="https://arxiv.org/format/2404.01588">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Hallucination Diversity-Aware Active Learning for Text Summarization </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Xia%2C+Y">Yu Xia</a>, <a href="/search/cs?searchtype=author&query=Liu%2C+X">Xu Liu</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+T">Tong Yu</a>, <a href="/search/cs?searchtype=author&query=Kim%2C+S">Sungchul Kim</a>, <a href="/search/cs?searchtype=author&query=Rossi%2C+R+A">Ryan A. Rossi</a>, <a href="/search/cs?searchtype=author&query=Rao%2C+A">Anup Rao</a>, <a href="/search/cs?searchtype=author&query=Mai%2C+T">Tung Mai</a>, <a href="/search/cs?searchtype=author&query=Li%2C+S">Shuai Li</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2404.01588v1-abstract-short" style="display: inline;"> Large Language Models (LLMs) have shown propensity to generate hallucinated outputs, i.e., texts that are factually incorrect or unsupported. Existing methods for alleviating hallucinations typically require costly human annotations to identify and correct hallucinations in LLM outputs. Moreover, most of these methods focus on a specific type of hallucination, e.g., entity or token errors, which l… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.01588v1-abstract-full').style.display = 'inline'; document.getElementById('2404.01588v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2404.01588v1-abstract-full" style="display: none;"> Large Language Models (LLMs) have shown propensity to generate hallucinated outputs, i.e., texts that are factually incorrect or unsupported. Existing methods for alleviating hallucinations typically require costly human annotations to identify and correct hallucinations in LLM outputs. Moreover, most of these methods focus on a specific type of hallucination, e.g., entity or token errors, which limits their effectiveness in addressing various types of hallucinations exhibited in LLM outputs. To our best knowledge, in this paper we propose the first active learning framework to alleviate LLM hallucinations, reducing costly human annotations of hallucination needed. By measuring fine-grained hallucinations from errors in semantic frame, discourse and content verifiability in text summarization, we propose HAllucination Diversity-Aware Sampling (HADAS) to select diverse hallucinations for annotations in active learning for LLM finetuning. Extensive experiments on three datasets and different backbone models demonstrate advantages of our method in effectively and efficiently mitigating LLM hallucinations. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.01588v1-abstract-full').style.display = 'none'; document.getElementById('2404.01588v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 1 April, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted to NAACL 2024</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2403.07213">arXiv:2403.07213</a> <span> [<a href="https://arxiv.org/pdf/2403.07213">pdf</a>, <a href="https://arxiv.org/format/2403.07213">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</span> </div> </div> <p class="title is-5 mathjax"> Which LLM to Play? Convergence-Aware Online Model Selection with Time-Increasing Bandits </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Xia%2C+Y">Yu Xia</a>, <a href="/search/cs?searchtype=author&query=Kong%2C+F">Fang Kong</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+T">Tong Yu</a>, <a href="/search/cs?searchtype=author&query=Guo%2C+L">Liya Guo</a>, <a href="/search/cs?searchtype=author&query=Rossi%2C+R+A">Ryan A. Rossi</a>, <a href="/search/cs?searchtype=author&query=Kim%2C+S">Sungchul Kim</a>, <a href="/search/cs?searchtype=author&query=Li%2C+S">Shuai Li</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2403.07213v1-abstract-short" style="display: inline;"> Web-based applications such as chatbots, search engines and news recommendations continue to grow in scale and complexity with the recent surge in the adoption of LLMs. Online model selection has thus garnered increasing attention due to the need to choose the best model among a diverse set while balancing task reward and exploration cost. Organizations faces decisions like whether to employ a cos… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.07213v1-abstract-full').style.display = 'inline'; document.getElementById('2403.07213v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2403.07213v1-abstract-full" style="display: none;"> Web-based applications such as chatbots, search engines and news recommendations continue to grow in scale and complexity with the recent surge in the adoption of LLMs. Online model selection has thus garnered increasing attention due to the need to choose the best model among a diverse set while balancing task reward and exploration cost. Organizations faces decisions like whether to employ a costly API-based LLM or a locally finetuned small LLM, weighing cost against performance. Traditional selection methods often evaluate every candidate model before choosing one, which are becoming impractical given the rising costs of training and finetuning LLMs. Moreover, it is undesirable to allocate excessive resources towards exploring poor-performing models. While some recent works leverage online bandit algorithm to manage such exploration-exploitation trade-off in model selection, they tend to overlook the increasing-then-converging trend in model performances as the model is iteratively finetuned, leading to less accurate predictions and suboptimal model selections. In this paper, we propose a time-increasing bandit algorithm TI-UCB, which effectively predicts the increase of model performances due to finetuning and efficiently balances exploration and exploitation in model selection. To further capture the converging points of models, we develop a change detection mechanism by comparing consecutive increase predictions. We theoretically prove that our algorithm achieves a logarithmic regret upper bound in a typical increasing bandit setting, which implies a fast convergence rate. The advantage of our method is also empirically validated through extensive experiments on classification model selection and online selection of LLMs. Our results highlight the importance of utilizing increasing-then-converging pattern for more efficient and economic model selection in the deployment of LLMs. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.07213v1-abstract-full').style.display = 'none'; document.getElementById('2403.07213v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 11 March, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted by WWW'24 (Oral)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2402.14195">arXiv:2402.14195</a> <span> [<a href="https://arxiv.org/pdf/2402.14195">pdf</a>, <a href="https://arxiv.org/format/2402.14195">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> Learning to Reduce: Optimal Representations of Structured Data in Prompting Large Language Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Lee%2C+Y">Younghun Lee</a>, <a href="/search/cs?searchtype=author&query=Kim%2C+S">Sungchul Kim</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+T">Tong Yu</a>, <a href="/search/cs?searchtype=author&query=Rossi%2C+R+A">Ryan A. Rossi</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+X">Xiang Chen</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2402.14195v1-abstract-short" style="display: inline;"> Large Language Models (LLMs) have been widely used as general-purpose AI agents showing comparable performance on many downstream tasks. However, existing work shows that it is challenging for LLMs to integrate structured data (e.g. KG, tables, DBs) into their prompts; LLMs need to either understand long text data or select the most relevant evidence prior to inference, and both approaches are not… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.14195v1-abstract-full').style.display = 'inline'; document.getElementById('2402.14195v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2402.14195v1-abstract-full" style="display: none;"> Large Language Models (LLMs) have been widely used as general-purpose AI agents showing comparable performance on many downstream tasks. However, existing work shows that it is challenging for LLMs to integrate structured data (e.g. KG, tables, DBs) into their prompts; LLMs need to either understand long text data or select the most relevant evidence prior to inference, and both approaches are not trivial. In this paper, we propose a framework, Learning to Reduce, that fine-tunes a language model to generate a reduced version of an input context, given a task description and context input. The model learns to reduce the input context using On-Policy Reinforcement Learning and aims to improve the reasoning performance of a fixed LLM. Experimental results illustrate that our model not only achieves comparable accuracies in selecting the relevant evidence from an input context, but also shows generalizability on different datasets. We further show that our model helps improve the LLM's performance on downstream tasks especially when the context is long. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.14195v1-abstract-full').style.display = 'none'; document.getElementById('2402.14195v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 21 February, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">5 pages</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2402.03388">arXiv:2402.03388</a> <span> [<a href="https://arxiv.org/pdf/2402.03388">pdf</a>, <a href="https://arxiv.org/format/2402.03388">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Information Retrieval">cs.IR</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1145/3583780.3614839">10.1145/3583780.3614839 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Delivery Optimized Discovery in Behavioral User Segmentation under Budget Constraint </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Chopra%2C+H">Harshita Chopra</a>, <a href="/search/cs?searchtype=author&query=Sinha%2C+A+R">Atanu R. Sinha</a>, <a href="/search/cs?searchtype=author&query=Choudhary%2C+S">Sunav Choudhary</a>, <a href="/search/cs?searchtype=author&query=Rossi%2C+R+A">Ryan A. Rossi</a>, <a href="/search/cs?searchtype=author&query=Indela%2C+P+K">Paavan Kumar Indela</a>, <a href="/search/cs?searchtype=author&query=Parwatala%2C+V+P">Veda Pranav Parwatala</a>, <a href="/search/cs?searchtype=author&query=Paul%2C+S">Srinjayee Paul</a>, <a href="/search/cs?searchtype=author&query=Maiti%2C+A">Aurghya Maiti</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2402.03388v2-abstract-short" style="display: inline;"> Users' behavioral footprints online enable firms to discover behavior-based user segments (or, segments) and deliver segment specific messages to users. Following the discovery of segments, delivery of messages to users through preferred media channels like Facebook and Google can be challenging, as only a portion of users in a behavior segment find match in a medium, and only a fraction of those… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.03388v2-abstract-full').style.display = 'inline'; document.getElementById('2402.03388v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2402.03388v2-abstract-full" style="display: none;"> Users' behavioral footprints online enable firms to discover behavior-based user segments (or, segments) and deliver segment specific messages to users. Following the discovery of segments, delivery of messages to users through preferred media channels like Facebook and Google can be challenging, as only a portion of users in a behavior segment find match in a medium, and only a fraction of those matched actually see the message (exposure). Even high quality discovery becomes futile when delivery fails. Many sophisticated algorithms exist for discovering behavioral segments; however, these ignore the delivery component. The problem is compounded because (i) the discovery is performed on the behavior data space in firms' data (e.g., user clicks), while the delivery is predicated on the static data space (e.g., geo, age) as defined by media; and (ii) firms work under budget constraint. We introduce a stochastic optimization based algorithm for delivery optimized discovery of behavioral user segmentation and offer new metrics to address the joint optimization. We leverage optimization under a budget constraint for delivery combined with a learning-based component for discovery. Extensive experiments on a public dataset from Google and a proprietary dataset show the effectiveness of our approach by simultaneously improving delivery metrics, reducing budget spend and achieving strong predictive performance in discovery. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.03388v2-abstract-full').style.display = 'none'; document.getElementById('2402.03388v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 15 March, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 4 February, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2402.01981">arXiv:2402.01981</a> <span> [<a href="https://arxiv.org/pdf/2402.01981">pdf</a>, <a href="https://arxiv.org/format/2402.01981">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computers and Society">cs.CY</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Self-Debiasing Large Language Models: Zero-Shot Recognition and Reduction of Stereotypes </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Gallegos%2C+I+O">Isabel O. Gallegos</a>, <a href="/search/cs?searchtype=author&query=Rossi%2C+R+A">Ryan A. Rossi</a>, <a href="/search/cs?searchtype=author&query=Barrow%2C+J">Joe Barrow</a>, <a href="/search/cs?searchtype=author&query=Tanjim%2C+M+M">Md Mehrab Tanjim</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+T">Tong Yu</a>, <a href="/search/cs?searchtype=author&query=Deilamsalehy%2C+H">Hanieh Deilamsalehy</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+R">Ruiyi Zhang</a>, <a href="/search/cs?searchtype=author&query=Kim%2C+S">Sungchul Kim</a>, <a href="/search/cs?searchtype=author&query=Dernoncourt%2C+F">Franck Dernoncourt</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2402.01981v1-abstract-short" style="display: inline;"> Large language models (LLMs) have shown remarkable advances in language generation and understanding but are also prone to exhibiting harmful social biases. While recognition of these behaviors has generated an abundance of bias mitigation techniques, most require modifications to the training data, model parameters, or decoding strategy, which may be infeasible without access to a trainable model… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.01981v1-abstract-full').style.display = 'inline'; document.getElementById('2402.01981v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2402.01981v1-abstract-full" style="display: none;"> Large language models (LLMs) have shown remarkable advances in language generation and understanding but are also prone to exhibiting harmful social biases. While recognition of these behaviors has generated an abundance of bias mitigation techniques, most require modifications to the training data, model parameters, or decoding strategy, which may be infeasible without access to a trainable model. In this work, we leverage the zero-shot capabilities of LLMs to reduce stereotyping in a technique we introduce as zero-shot self-debiasing. With two approaches, self-debiasing via explanation and self-debiasing via reprompting, we show that self-debiasing can significantly reduce the degree of stereotyping across nine different social groups while relying only on the LLM itself and a simple prompt, with explanations correctly identifying invalid assumptions and reprompting delivering the greatest reductions in bias. We hope this work opens inquiry into other zero-shot techniques for bias mitigation. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.01981v1-abstract-full').style.display = 'none'; document.getElementById('2402.01981v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 2 February, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2310.13227">arXiv:2310.13227</a> <span> [<a href="https://arxiv.org/pdf/2310.13227">pdf</a>, <a href="https://arxiv.org/format/2310.13227">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> ToolChain*: Efficient Action Space Navigation in Large Language Models with A* Search </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Zhuang%2C+Y">Yuchen Zhuang</a>, <a href="/search/cs?searchtype=author&query=Chen%2C+X">Xiang Chen</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+T">Tong Yu</a>, <a href="/search/cs?searchtype=author&query=Mitra%2C+S">Saayan Mitra</a>, <a href="/search/cs?searchtype=author&query=Bursztyn%2C+V">Victor Bursztyn</a>, <a href="/search/cs?searchtype=author&query=Rossi%2C+R+A">Ryan A. Rossi</a>, <a href="/search/cs?searchtype=author&query=Sarkhel%2C+S">Somdeb Sarkhel</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+C">Chao Zhang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2310.13227v1-abstract-short" style="display: inline;"> Large language models (LLMs) have demonstrated powerful decision-making and planning capabilities in solving complicated real-world problems. LLM-based autonomous agents can interact with diverse tools (e.g., functional APIs) and generate solution plans that execute a series of API function calls in a step-by-step manner. The multitude of candidate API function calls significantly expands the acti… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2310.13227v1-abstract-full').style.display = 'inline'; document.getElementById('2310.13227v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2310.13227v1-abstract-full" style="display: none;"> Large language models (LLMs) have demonstrated powerful decision-making and planning capabilities in solving complicated real-world problems. LLM-based autonomous agents can interact with diverse tools (e.g., functional APIs) and generate solution plans that execute a series of API function calls in a step-by-step manner. The multitude of candidate API function calls significantly expands the action space, amplifying the critical need for efficient action space navigation. However, existing methods either struggle with unidirectional exploration in expansive action spaces, trapped into a locally optimal solution, or suffer from exhaustively traversing all potential actions, causing inefficient navigation. To address these issues, we propose ToolChain*, an efficient tree search-based planning algorithm for LLM-based agents. It formulates the entire action space as a decision tree, where each node represents a possible API function call involved in a solution plan. By incorporating the A* search algorithm with task-specific cost function design, it efficiently prunes high-cost branches that may involve incorrect actions, identifying the most low-cost valid path as the solution. Extensive experiments on multiple tool-use and reasoning tasks demonstrate that ToolChain* efficiently balances exploration and exploitation within an expansive action space. It outperforms state-of-the-art baselines on planning and reasoning tasks by 3.1% and 3.5% on average while requiring 7.35x and 2.31x less time, respectively. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2310.13227v1-abstract-full').style.display = 'none'; document.getElementById('2310.13227v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 19 October, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2309.09400">arXiv:2309.09400</a> <span> [<a href="https://arxiv.org/pdf/2309.09400">pdf</a>, <a href="https://arxiv.org/format/2309.09400">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> CulturaX: A Cleaned, Enormous, and Multilingual Dataset for Large Language Models in 167 Languages </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Nguyen%2C+T">Thuat Nguyen</a>, <a href="/search/cs?searchtype=author&query=Van+Nguyen%2C+C">Chien Van Nguyen</a>, <a href="/search/cs?searchtype=author&query=Lai%2C+V+D">Viet Dac Lai</a>, <a href="/search/cs?searchtype=author&query=Man%2C+H">Hieu Man</a>, <a href="/search/cs?searchtype=author&query=Ngo%2C+N+T">Nghia Trung Ngo</a>, <a href="/search/cs?searchtype=author&query=Dernoncourt%2C+F">Franck Dernoncourt</a>, <a href="/search/cs?searchtype=author&query=Rossi%2C+R+A">Ryan A. Rossi</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+T+H">Thien Huu Nguyen</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2309.09400v1-abstract-short" style="display: inline;"> The driving factors behind the development of large language models (LLMs) with impressive learning capabilities are their colossal model sizes and extensive training datasets. Along with the progress in natural language processing, LLMs have been frequently made accessible to the public to foster deeper investigation and applications. However, when it comes to training datasets for these LLMs, es… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2309.09400v1-abstract-full').style.display = 'inline'; document.getElementById('2309.09400v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2309.09400v1-abstract-full" style="display: none;"> The driving factors behind the development of large language models (LLMs) with impressive learning capabilities are their colossal model sizes and extensive training datasets. Along with the progress in natural language processing, LLMs have been frequently made accessible to the public to foster deeper investigation and applications. However, when it comes to training datasets for these LLMs, especially the recent state-of-the-art models, they are often not fully disclosed. Creating training data for high-performing LLMs involves extensive cleaning and deduplication to ensure the necessary level of quality. The lack of transparency for training data has thus hampered research on attributing and addressing hallucination and bias issues in LLMs, hindering replication efforts and further advancements in the community. These challenges become even more pronounced in multilingual learning scenarios, where the available multilingual text datasets are often inadequately collected and cleaned. Consequently, there is a lack of open-source and readily usable dataset to effectively train LLMs in multiple languages. To overcome this issue, we present CulturaX, a substantial multilingual dataset with 6.3 trillion tokens in 167 languages, tailored for LLM development. Our dataset undergoes meticulous cleaning and deduplication through a rigorous pipeline of multiple stages to accomplish the best quality for model training, including language identification, URL-based filtering, metric-based cleaning, document refinement, and data deduplication. CulturaX is fully released to the public in HuggingFace to facilitate research and advancements in multilingual LLMs: https://huggingface.co/datasets/uonlp/CulturaX. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2309.09400v1-abstract-full').style.display = 'none'; document.getElementById('2309.09400v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 17 September, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Ongoing Work</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2309.08872">arXiv:2309.08872</a> <span> [<a href="https://arxiv.org/pdf/2309.08872">pdf</a>, <a href="https://arxiv.org/format/2309.08872">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> PDFTriage: Question Answering over Long, Structured Documents </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Saad-Falcon%2C+J">Jon Saad-Falcon</a>, <a href="/search/cs?searchtype=author&query=Barrow%2C+J">Joe Barrow</a>, <a href="/search/cs?searchtype=author&query=Siu%2C+A">Alexa Siu</a>, <a href="/search/cs?searchtype=author&query=Nenkova%2C+A">Ani Nenkova</a>, <a href="/search/cs?searchtype=author&query=Yoon%2C+D+S">David Seunghyun Yoon</a>, <a href="/search/cs?searchtype=author&query=Rossi%2C+R+A">Ryan A. Rossi</a>, <a href="/search/cs?searchtype=author&query=Dernoncourt%2C+F">Franck Dernoncourt</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2309.08872v2-abstract-short" style="display: inline;"> Large Language Models (LLMs) have issues with document question answering (QA) in situations where the document is unable to fit in the small context length of an LLM. To overcome this issue, most existing works focus on retrieving the relevant context from the document, representing them as plain text. However, documents such as PDFs, web pages, and presentations are naturally structured with dif… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2309.08872v2-abstract-full').style.display = 'inline'; document.getElementById('2309.08872v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2309.08872v2-abstract-full" style="display: none;"> Large Language Models (LLMs) have issues with document question answering (QA) in situations where the document is unable to fit in the small context length of an LLM. To overcome this issue, most existing works focus on retrieving the relevant context from the document, representing them as plain text. However, documents such as PDFs, web pages, and presentations are naturally structured with different pages, tables, sections, and so on. Representing such structured documents as plain text is incongruous with the user's mental model of these documents with rich structure. When a system has to query the document for context, this incongruity is brought to the fore, and seemingly trivial questions can trip up the QA system. To bridge this fundamental gap in handling structured documents, we propose an approach called PDFTriage that enables models to retrieve the context based on either structure or content. Our experiments demonstrate the effectiveness of the proposed PDFTriage-augmented models across several classes of questions where existing retrieval-augmented LLMs fail. To facilitate further research on this fundamental problem, we release our benchmark dataset consisting of 900+ human-generated questions over 80 structured documents from 10 different categories of question types for document QA. Our code and datasets will be released soon on Github. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2309.08872v2-abstract-full').style.display = 'none'; document.getElementById('2309.08872v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 8 November, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 16 September, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2309.00770">arXiv:2309.00770</a> <span> [<a href="https://arxiv.org/pdf/2309.00770">pdf</a>, <a href="https://arxiv.org/format/2309.00770">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computers and Society">cs.CY</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Bias and Fairness in Large Language Models: A Survey </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Gallegos%2C+I+O">Isabel O. Gallegos</a>, <a href="/search/cs?searchtype=author&query=Rossi%2C+R+A">Ryan A. Rossi</a>, <a href="/search/cs?searchtype=author&query=Barrow%2C+J">Joe Barrow</a>, <a href="/search/cs?searchtype=author&query=Tanjim%2C+M+M">Md Mehrab Tanjim</a>, <a href="/search/cs?searchtype=author&query=Kim%2C+S">Sungchul Kim</a>, <a href="/search/cs?searchtype=author&query=Dernoncourt%2C+F">Franck Dernoncourt</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+T">Tong Yu</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+R">Ruiyi Zhang</a>, <a href="/search/cs?searchtype=author&query=Ahmed%2C+N+K">Nesreen K. Ahmed</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2309.00770v3-abstract-short" style="display: inline;"> Rapid advancements of large language models (LLMs) have enabled the processing, understanding, and generation of human-like text, with increasing integration into systems that touch our social sphere. Despite this success, these models can learn, perpetuate, and amplify harmful social biases. In this paper, we present a comprehensive survey of bias evaluation and mitigation techniques for LLMs. We… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2309.00770v3-abstract-full').style.display = 'inline'; document.getElementById('2309.00770v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2309.00770v3-abstract-full" style="display: none;"> Rapid advancements of large language models (LLMs) have enabled the processing, understanding, and generation of human-like text, with increasing integration into systems that touch our social sphere. Despite this success, these models can learn, perpetuate, and amplify harmful social biases. In this paper, we present a comprehensive survey of bias evaluation and mitigation techniques for LLMs. We first consolidate, formalize, and expand notions of social bias and fairness in natural language processing, defining distinct facets of harm and introducing several desiderata to operationalize fairness for LLMs. We then unify the literature by proposing three intuitive taxonomies, two for bias evaluation, namely metrics and datasets, and one for mitigation. Our first taxonomy of metrics for bias evaluation disambiguates the relationship between metrics and evaluation datasets, and organizes metrics by the different levels at which they operate in a model: embeddings, probabilities, and generated text. Our second taxonomy of datasets for bias evaluation categorizes datasets by their structure as counterfactual inputs or prompts, and identifies the targeted harms and social groups; we also release a consolidation of publicly-available datasets for improved access. Our third taxonomy of techniques for bias mitigation classifies methods by their intervention during pre-processing, in-training, intra-processing, and post-processing, with granular subcategories that elucidate research trends. Finally, we identify open problems and challenges for future work. Synthesizing a wide range of recent research, we aim to provide a clear guide of the existing literature that empowers researchers and practitioners to better understand and prevent the propagation of bias in LLMs. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2309.00770v3-abstract-full').style.display = 'none'; document.getElementById('2309.00770v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 12 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 1 September, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted at Computational Linguistics, Volume 50, Number 3</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2308.11730">arXiv:2308.11730</a> <span> [<a href="https://arxiv.org/pdf/2308.11730">pdf</a>, <a href="https://arxiv.org/format/2308.11730">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Information Retrieval">cs.IR</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Knowledge Graph Prompting for Multi-Document Question Answering </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yu Wang</a>, <a href="/search/cs?searchtype=author&query=Lipka%2C+N">Nedim Lipka</a>, <a href="/search/cs?searchtype=author&query=Rossi%2C+R+A">Ryan A. Rossi</a>, <a href="/search/cs?searchtype=author&query=Siu%2C+A">Alexa Siu</a>, <a href="/search/cs?searchtype=author&query=Zhang%2C+R">Ruiyi Zhang</a>, <a href="/search/cs?searchtype=author&query=Derr%2C+T">Tyler Derr</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2308.11730v3-abstract-short" style="display: inline;"> The `pre-train, prompt, predict' paradigm of large language models (LLMs) has achieved remarkable success in open-domain question answering (OD-QA). However, few works explore this paradigm in the scenario of multi-document question answering (MD-QA), a task demanding a thorough understanding of the logical associations among the contents and structures of different documents. To fill this crucial… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2308.11730v3-abstract-full').style.display = 'inline'; document.getElementById('2308.11730v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2308.11730v3-abstract-full" style="display: none;"> The `pre-train, prompt, predict' paradigm of large language models (LLMs) has achieved remarkable success in open-domain question answering (OD-QA). However, few works explore this paradigm in the scenario of multi-document question answering (MD-QA), a task demanding a thorough understanding of the logical associations among the contents and structures of different documents. To fill this crucial gap, we propose a Knowledge Graph Prompting (KGP) method to formulate the right context in prompting LLMs for MD-QA, which consists of a graph construction module and a graph traversal module. For graph construction, we create a knowledge graph (KG) over multiple documents with nodes symbolizing passages or document structures (e.g., pages/tables), and edges denoting the semantic/lexical similarity between passages or intra-document structural relations. For graph traversal, we design an LLM-based graph traversal agent that navigates across nodes and gathers supporting passages assisting LLMs in MD-QA. The constructed graph serves as the global ruler that regulates the transitional space among passages and reduces retrieval latency. Concurrently, the graph traversal agent acts as a local navigator that gathers pertinent context to progressively approach the question and guarantee retrieval quality. Extensive experiments underscore the efficacy of KGP for MD-QA, signifying the potential of leveraging graphs in enhancing the prompt design for LLMs. Our code: https://github.com/YuWVandy/KG-LLM-MDQA. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2308.11730v3-abstract-full').style.display = 'none'; document.getElementById('2308.11730v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 25 December, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 22 August, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2307.16039">arXiv:2307.16039</a> <span> [<a href="https://arxiv.org/pdf/2307.16039">pdf</a>, <a href="https://arxiv.org/format/2307.16039">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Okapi: Instruction-tuned Large Language Models in Multiple Languages with Reinforcement Learning from Human Feedback </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Lai%2C+V+D">Viet Dac Lai</a>, <a href="/search/cs?searchtype=author&query=Van+Nguyen%2C+C">Chien Van Nguyen</a>, <a href="/search/cs?searchtype=author&query=Ngo%2C+N+T">Nghia Trung Ngo</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+T">Thuat Nguyen</a>, <a href="/search/cs?searchtype=author&query=Dernoncourt%2C+F">Franck Dernoncourt</a>, <a href="/search/cs?searchtype=author&query=Rossi%2C+R+A">Ryan A. Rossi</a>, <a href="/search/cs?searchtype=author&query=Nguyen%2C+T+H">Thien Huu Nguyen</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2307.16039v2-abstract-short" style="display: inline;"> A key technology for the development of large language models (LLMs) involves instruction tuning that helps align the models' responses with human expectations to realize impressive learning abilities. Two major approaches for instruction tuning characterize supervised fine-tuning (SFT) and reinforcement learning from human feedback (RLHF), which are currently applied to produce the best commercia… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2307.16039v2-abstract-full').style.display = 'inline'; document.getElementById('2307.16039v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2307.16039v2-abstract-full" style="display: none;"> A key technology for the development of large language models (LLMs) involves instruction tuning that helps align the models' responses with human expectations to realize impressive learning abilities. Two major approaches for instruction tuning characterize supervised fine-tuning (SFT) and reinforcement learning from human feedback (RLHF), which are currently applied to produce the best commercial LLMs (e.g., ChatGPT). To improve the accessibility of LLMs for research and development efforts, various instruction-tuned open-source LLMs have also been introduced recently, e.g., Alpaca, Vicuna, to name a few. However, existing open-source LLMs have only been instruction-tuned for English and a few popular languages, thus hindering their impacts and accessibility to many other languages in the world. Among a few very recent work to explore instruction tuning for LLMs in multiple languages, SFT has been used as the only approach to instruction-tune LLMs for multiple languages. This has left a significant gap for fine-tuned LLMs based on RLHF in diverse languages and raised important questions on how RLHF can boost the performance of multilingual instruction tuning. To overcome this issue, we present Okapi, the first system with instruction-tuned LLMs based on RLHF for multiple languages. Okapi introduces instruction and response-ranked data in 26 diverse languages to facilitate the experiments and development of future multilingual LLM research. We also present benchmark datasets to enable the evaluation of generative LLMs in multiple languages. Our experiments demonstrate the advantages of RLHF for multilingual instruction over SFT for different base models and datasets. Our framework and resources are released at https://github.com/nlp-uoregon/Okapi. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2307.16039v2-abstract-full').style.display = 'none'; document.getElementById('2307.16039v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 1 August, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 29 July, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2307.10867">arXiv:2307.10867</a> <span> [<a href="https://arxiv.org/pdf/2307.10867">pdf</a>, <a href="https://arxiv.org/format/2307.10867">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computer Vision and Pattern Recognition">cs.CV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> FigCaps-HF: A Figure-to-Caption Generative Framework and Benchmark with Human Feedback </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Singh%2C+A">Ashish Singh</a>, <a href="/search/cs?searchtype=author&query=Agarwal%2C+P">Prateek Agarwal</a>, <a href="/search/cs?searchtype=author&query=Huang%2C+Z">Zixuan Huang</a>, <a href="/search/cs?searchtype=author&query=Singh%2C+A">Arpita Singh</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+T">Tong Yu</a>, <a href="/search/cs?searchtype=author&query=Kim%2C+S">Sungchul Kim</a>, <a href="/search/cs?searchtype=author&query=Bursztyn%2C+V">Victor Bursztyn</a>, <a href="/search/cs?searchtype=author&query=Vlassis%2C+N">Nikos Vlassis</a>, <a href="/search/cs?searchtype=author&query=Rossi%2C+R+A">Ryan A. Rossi</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2307.10867v1-abstract-short" style="display: inline;"> Captions are crucial for understanding scientific visualizations and documents. Existing captioning methods for scientific figures rely on figure-caption pairs extracted from documents for training, many of which fall short with respect to metrics like helpfulness, explainability, and visual-descriptiveness [15] leading to generated captions being misaligned with reader preferences. To enable the… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2307.10867v1-abstract-full').style.display = 'inline'; document.getElementById('2307.10867v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2307.10867v1-abstract-full" style="display: none;"> Captions are crucial for understanding scientific visualizations and documents. Existing captioning methods for scientific figures rely on figure-caption pairs extracted from documents for training, many of which fall short with respect to metrics like helpfulness, explainability, and visual-descriptiveness [15] leading to generated captions being misaligned with reader preferences. To enable the generation of high-quality figure captions, we introduce FigCaps-HF a new framework for figure-caption generation that can incorporate domain expert feedback in generating captions optimized for reader preferences. Our framework comprises of 1) an automatic method for evaluating quality of figure-caption pairs, 2) a novel reinforcement learning with human feedback (RLHF) method to optimize a generative figure-to-caption model for reader preferences. We demonstrate the effectiveness of our simple learning framework by improving performance over standard fine-tuning across different types of models. In particular, when using BLIP as the base model, our RLHF framework achieves a mean gain of 35.7%, 16.9%, and 9% in ROUGE, BLEU, and Meteor, respectively. Finally, we release a large-scale benchmark dataset with human feedback on figure-caption pairs to enable further evaluation and development of RLHF techniques for this problem. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2307.10867v1-abstract-full').style.display = 'none'; document.getElementById('2307.10867v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 20 July, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">19 pages, 4 figures. Benchmark Documentation: https://figcapshf.github.io/</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2307.03929">arXiv:2307.03929</a> <span> [<a href="https://arxiv.org/pdf/2307.03929">pdf</a>, <a href="https://arxiv.org/format/2307.03929">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Information Retrieval">cs.IR</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Social and Information Networks">cs.SI</span> </div> </div> <p class="title is-5 mathjax"> Fairness-Aware Graph Neural Networks: A Survey </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Chen%2C+A">April Chen</a>, <a href="/search/cs?searchtype=author&query=Rossi%2C+R+A">Ryan A. Rossi</a>, <a href="/search/cs?searchtype=author&query=Park%2C+N">Namyong Park</a>, <a href="/search/cs?searchtype=author&query=Trivedi%2C+P">Puja Trivedi</a>, <a href="/search/cs?searchtype=author&query=Wang%2C+Y">Yu Wang</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+T">Tong Yu</a>, <a href="/search/cs?searchtype=author&query=Kim%2C+S">Sungchul Kim</a>, <a href="/search/cs?searchtype=author&query=Dernoncourt%2C+F">Franck Dernoncourt</a>, <a href="/search/cs?searchtype=author&query=Ahmed%2C+N+K">Nesreen K. Ahmed</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2307.03929v1-abstract-short" style="display: inline;"> Graph Neural Networks (GNNs) have become increasingly important due to their representational power and state-of-the-art predictive performance on many fundamental learning tasks. Despite this success, GNNs suffer from fairness issues that arise as a result of the underlying graph data and the fundamental aggregation mechanism that lies at the heart of the large class of GNN models. In this articl… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2307.03929v1-abstract-full').style.display = 'inline'; document.getElementById('2307.03929v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2307.03929v1-abstract-full" style="display: none;"> Graph Neural Networks (GNNs) have become increasingly important due to their representational power and state-of-the-art predictive performance on many fundamental learning tasks. Despite this success, GNNs suffer from fairness issues that arise as a result of the underlying graph data and the fundamental aggregation mechanism that lies at the heart of the large class of GNN models. In this article, we examine and categorize fairness techniques for improving the fairness of GNNs. Previous work on fair GNN models and techniques are discussed in terms of whether they focus on improving fairness during a preprocessing step, during training, or in a post-processing phase. Furthermore, we discuss how such techniques can be used together whenever appropriate, and highlight the advantages and intuition as well. We also introduce an intuitive taxonomy for fairness evaluation metrics including graph-level fairness, neighborhood-level fairness, embedding-level fairness, and prediction-level fairness metrics. In addition, graph datasets that are useful for benchmarking the fairness of GNN models are summarized succinctly. Finally, we highlight key open problems and challenges that remain to be addressed. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2307.03929v1-abstract-full').style.display = 'none'; document.getElementById('2307.03929v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 8 July, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2306.11855">arXiv:2306.11855</a> <span> [<a href="https://arxiv.org/pdf/2306.11855">pdf</a>, <a href="https://arxiv.org/format/2306.11855">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Methodology">stat.ME</span> </div> </div> <p class="title is-5 mathjax"> A Model-free Closeness-of-influence Test for Features in Supervised Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Mehrabi%2C+M">Mohammad Mehrabi</a>, <a href="/search/cs?searchtype=author&query=Rossi%2C+R+A">Ryan A. Rossi</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2306.11855v1-abstract-short" style="display: inline;"> Understanding the effect of a feature vector $x \in \mathbb{R}^d$ on the response value (label) $y \in \mathbb{R}$ is the cornerstone of many statistical learning problems. Ideally, it is desired to understand how a set of collected features combine together and influence the response value, but this problem is notoriously difficult, due to the high-dimensionality of data and limited number of lab… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2306.11855v1-abstract-full').style.display = 'inline'; document.getElementById('2306.11855v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2306.11855v1-abstract-full" style="display: none;"> Understanding the effect of a feature vector $x \in \mathbb{R}^d$ on the response value (label) $y \in \mathbb{R}$ is the cornerstone of many statistical learning problems. Ideally, it is desired to understand how a set of collected features combine together and influence the response value, but this problem is notoriously difficult, due to the high-dimensionality of data and limited number of labeled data points, among many others. In this work, we take a new perspective on this problem, and we study the question of assessing the difference of influence that the two given features have on the response value. We first propose a notion of closeness for the influence of features, and show that our definition recovers the familiar notion of the magnitude of coefficients in the parametric model. We then propose a novel method to test for the closeness of influence in general model-free supervised learning problems. Our proposed test can be used with finite number of samples with control on type I error rate, no matter the ground truth conditional law $\mathcal{L}(Y |X)$. We analyze the power of our test for two general learning problems i) linear regression, and ii) binary classification under mixture of Gaussian models, and show that under the proper choice of score function, an internal component of our test, with sufficient number of samples will achieve full statistical power. We evaluate our findings through extensive numerical simulations, specifically we adopt the datamodel framework (Ilyas, et al., 2022) for CIFAR-10 dataset to identify pairs of training samples with different influence on the trained model via optional black box training mechanisms. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2306.11855v1-abstract-full').style.display = 'none'; document.getElementById('2306.11855v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 20 June, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2305.10434">arXiv:2305.10434</a> <span> [<a href="https://arxiv.org/pdf/2305.10434">pdf</a>, <a href="https://arxiv.org/format/2305.10434">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Learning the Visualness of Text Using Large Vision-Language Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Verma%2C+G">Gaurav Verma</a>, <a href="/search/cs?searchtype=author&query=Rossi%2C+R+A">Ryan A. Rossi</a>, <a href="/search/cs?searchtype=author&query=Tensmeyer%2C+C">Christopher Tensmeyer</a>, <a href="/search/cs?searchtype=author&query=Gu%2C+J">Jiuxiang Gu</a>, <a href="/search/cs?searchtype=author&query=Nenkova%2C+A">Ani Nenkova</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2305.10434v2-abstract-short" style="display: inline;"> Visual text evokes an image in a person's mind, while non-visual text fails to do so. A method to automatically detect visualness in text will enable text-to-image retrieval and generation models to augment text with relevant images. This is particularly challenging with long-form text as text-to-image generation and retrieval models are often triggered for text that is designed to be explicitly v… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.10434v2-abstract-full').style.display = 'inline'; document.getElementById('2305.10434v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2305.10434v2-abstract-full" style="display: none;"> Visual text evokes an image in a person's mind, while non-visual text fails to do so. A method to automatically detect visualness in text will enable text-to-image retrieval and generation models to augment text with relevant images. This is particularly challenging with long-form text as text-to-image generation and retrieval models are often triggered for text that is designed to be explicitly visual in nature, whereas long-form text could contain many non-visual sentences. To this end, we curate a dataset of 3,620 English sentences and their visualness scores provided by multiple human annotators. We also propose a fine-tuning strategy that adapts large vision-language models like CLIP by modifying the model's contrastive learning objective to map text identified as non-visual to a common NULL image while matching visual text to their corresponding images in the document. We evaluate the proposed approach on its ability to (i) classify visual and non-visual text accurately, and (ii) attend over words that are identified as visual in psycholinguistic studies. Empirical evaluation indicates that our approach performs better than several heuristics and baseline models for the proposed task. Furthermore, to highlight the importance of modeling the visualness of text, we conduct qualitative analyses of text-to-image generation systems like DALL-E. Project webpage: https://gaurav22verma.github.io/text-visualness/ <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.10434v2-abstract-full').style.display = 'none'; document.getElementById('2305.10434v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 22 October, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 11 May, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted at EMNLP 2023 (Main, long); 9 pages, 5 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2303.15652">arXiv:2303.15652</a> <span> [<a href="https://arxiv.org/pdf/2303.15652">pdf</a>, <a href="https://arxiv.org/format/2303.15652">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Data Structures and Algorithms">cs.DS</span> </div> </div> <p class="title is-5 mathjax"> Structured Dynamic Pricing: Optimal Regret in a Global Shrinkage Model </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Bhuyan%2C+R+R">Rashmi Ranjan Bhuyan</a>, <a href="/search/cs?searchtype=author&query=Javanmard%2C+A">Adel Javanmard</a>, <a href="/search/cs?searchtype=author&query=Kim%2C+S">Sungchul Kim</a>, <a href="/search/cs?searchtype=author&query=Mukherjee%2C+G">Gourab Mukherjee</a>, <a href="/search/cs?searchtype=author&query=Rossi%2C+R+A">Ryan A. Rossi</a>, <a href="/search/cs?searchtype=author&query=Yu%2C+T">Tong Yu</a>, <a href="/search/cs?searchtype=author&query=Zhao%2C+H">Handong Zhao</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2303.15652v2-abstract-short" style="display: inline;"> We consider dynamic pricing strategies in a streamed longitudinal data set-up where the objective is to maximize, over time, the cumulative profit across a large number of customer segments. We consider a dynamic model with the consumers' preferences as well as price sensitivity varying over time. Building on the well-known finding that consumers sharing similar characteristics act in similar ways… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2303.15652v2-abstract-full').style.display = 'inline'; document.getElementById('2303.15652v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2303.15652v2-abstract-full" style="display: none;"> We consider dynamic pricing strategies in a streamed longitudinal data set-up where the objective is to maximize, over time, the cumulative profit across a large number of customer segments. We consider a dynamic model with the consumers' preferences as well as price sensitivity varying over time. Building on the well-known finding that consumers sharing similar characteristics act in similar ways, we consider a global shrinkage structure, which assumes that the consumers' preferences across the different segments can be well approximated by a spatial autoregressive (SAR) model. In such a streamed longitudinal set-up, we measure the performance of a dynamic pricing policy via regret, which is the expected revenue loss compared to a clairvoyant that knows the sequence of model parameters in advance. We propose a pricing policy based on penalized stochastic gradient descent (PSGD) and explicitly characterize its regret as functions of time, the temporal variability in the model parameters as well as the strength of the auto-correlation network structure spanning the varied customer segments. Our regret analysis results not only demonstrate asymptotic optimality of the proposed policy but also show that for policy planning it is essential to incorporate available structural information as policies based on unshrunken models are highly sub-optimal in the aforementioned set-up. We conduct simulation experiments across a wide range of regimes as well as real-world networks based studies and report encouraging performance for our proposed method. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2303.15652v2-abstract-full').style.display = 'none'; document.getElementById('2303.15652v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 13 October, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 27 March, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">43 pages, 10 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2303.01575">arXiv:2303.01575</a> <span> [<a href="https://arxiv.org/pdf/2303.01575">pdf</a>, <a href="https://arxiv.org/format/2303.01575">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Human-Computer Interaction">cs.HC</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1145/3544548.3581509">10.1145/3544548.3581509 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> DataPilot: Utilizing Quality and Usage Information for Subset Selection during Visual Data Preparation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&query=Narechania%2C+A">Arpit Narechania</a>, <a href="/search/cs?searchtype=author&query=Du%2C+F">Fan Du</a>, <a href="/search/cs?searchtype=author&query=Sinha%2C+A+R">Atanu R Sinha</a>, <a href="/search/cs?searchtype=author&query=Rossi%2C+R+A">Ryan A. Rossi</a>, <a href="/search/cs?searchtype=author&query=Hoffswell%2C+J">Jane Hoffswell</a>, <a href="/search/cs?searchtype=author&query=Guo%2C+S">Shunan Guo</a>, <a href="/search/cs?searchtype=author&query=Koh%2C+E">Eunyee Koh</a>, <a href="/search/cs?searchtype=author&query=Navathe%2C+S+B">Shamkant B. Navathe</a>, <a href="/search/cs?searchtype=author&query=Endert%2C+A">Alex Endert</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2303.01575v1-abstract-short" style="display: inline;"> Selecting relevant data subsets from large, unfamiliar datasets can be difficult. We address this challenge by modeling and visualizing two kinds of auxiliary information: (1) quality - the validity and appropriateness of data required to perform certain analytical tasks; and (2) usage - the historical utilization characteristics of data across multiple users. Through a design study with 14 data w… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2303.01575v1-abstract-full').style.display = 'inline'; document.getElementById('2303.01575v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2303.01575v1-abstract-full" style="display: none;"> Selecting relevant data subsets from large, unfamiliar datasets can be difficult. We address this challenge by modeling and visualizing two kinds of auxiliary information: (1) quality - the validity and appropriateness of data required to perform certain analytical tasks; and (2) usage - the historical utilization characteristics of data across multiple users. Through a design study with 14 data workers, we integrate this information into a visual data preparation and analysis tool, DataPilot. DataPilot presents visual cues about "the good, the bad, and the ugly" aspects of data and provides graphical user interface controls as interaction affordances, guiding users to perform subset selection. Through a study with 36 participants, we investigate how DataPilot helps users navigate a large, unfamiliar tabular dataset, prepare a relevant subset, and build a visualization dashboard. We find that users selected smaller, effective subsets with higher quality and usage, and with greater success and confidence. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2303.01575v1-abstract-full').style.display = 'none'; document.getElementById('2303.01575v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 2 March, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">18 pages, 5 figures, 1 table, ACM CHI 2023</span> </p> </li> </ol> <nav class="pagination is-small is-centered breathe-horizontal" role="navigation" aria-label="pagination"> <a href="" class="pagination-previous is-invisible">Previous </a> <a href="/search/?searchtype=author&query=Rossi%2C+R+A&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Rossi%2C+R+A&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Rossi%2C+R+A&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </a> </li> <li> <a href="/search/?searchtype=author&query=Rossi%2C+R+A&start=100" class="pagination-link " aria-label="Page 3" aria-current="page">3 </a> </li> </ul> </nav> <div class="is-hidden-tablet">  <span class="help" style="display: inline-block;"><a href="https://github.com/arXiv/arxiv-search/releases">Search v0.5.6 released 2020-02-24</a>  </span> </div> </div> </main> <footer> <div class="columns is-desktop" role="navigation" aria-label="Secondary">  <div class="column"> <div class="columns"> <div class="column"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/about">About</a></li> <li><a href="https://info.arxiv.org/help">Help</a></li> </ul> </div> <div class="column"> <ul class="nav-spaced"> <li> <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><title>contact arXiv</title><desc>Click here to contact arXiv</desc><path d="M502.3 190.8c3.9-3.1 9.7-.2 9.7 4.7V400c0 26.5-21.5 48-48 48H48c-26.5 0-48-21.5-48-48V195.6c0-5 5.7-7.8 9.7-4.7 22.4 17.4 52.1 39.5 154.1 113.6 21.1 15.4 56.7 47.8 92.2 47.6 35.7.3 72-32.8 92.3-47.6 102-74.1 131.6-96.3 154-113.7zM256 320c23.2.4 56.6-29.2 73.4-41.4 132.7-96.3 142.8-104.7 173.4-128.7 5.8-4.5 9.2-11.5 9.2-18.9v-19c0-26.5-21.5-48-48-48H48C21.5 64 0 85.5 0 112v19c0 7.4 3.4 14.3 9.2 18.9 30.6 23.9 40.7 32.4 173.4 128.7 16.8 12.2 50.2 41.8 73.4 41.4z"/></svg> <a href="https://info.arxiv.org/help/contact.html"> Contact</a> </li> <li> <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><title>subscribe to arXiv mailings</title><desc>Click here to subscribe</desc><path d="M476 3.2L12.5 270.6c-18.1 10.4-15.8 35.6 2.2 43.2L121 358.4l287.3-253.2c5.5-4.9 13.3 2.6 8.6 8.3L176 407v80.5c0 23.6 28.5 32.9 42.5 15.8L282 426l124.6 52.2c14.2 6 30.4-2.9 33-18.2l72-432C515 7.8 493.3-6.8 476 3.2z"/></svg> <a href="https://info.arxiv.org/help/subscribe"> Subscribe</a> </li> </ul> </div> </div> </div>   <div class="column"> <div class="columns"> <div class="column"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/help/license/index.html">Copyright</a></li> <li><a href="https://info.arxiv.org/help/policies/privacy_policy.html">Privacy Policy</a></li> </ul> </div> <div class="column sorry-app-links"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/help/web_accessibility.html">Web Accessibility Assistance</a></li> <li> <p class="help"> <a class="a11y-main-link" href="https://status.arxiv.org" target="_blank">arXiv Operational Status <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 256 512" class="icon filter-dark_grey" role="presentation"><path d="M224.3 273l-136 136c-9.4 9.4-24.6 9.4-33.9 0l-22.6-22.6c-9.4-9.4-9.4-24.6 0-33.9l96.4-96.4-96.4-96.4c-9.4-9.4-9.4-24.6 0-33.9L54.3 103c9.4-9.4 24.6-9.4 33.9 0l136 136c9.5 9.4 9.5 24.6.1 34z"/></svg></a><br> Get status notifications via <a class="is-link" href="https://subscribe.sorryapp.com/24846f03/email/new" target="_blank"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><path d="M502.3 190.8c3.9-3.1 9.7-.2 9.7 4.7V400c0 26.5-21.5 48-48 48H48c-26.5 0-48-21.5-48-48V195.6c0-5 5.7-7.8 9.7-4.7 22.4 17.4 52.1 39.5 154.1 113.6 21.1 15.4 56.7 47.8 92.2 47.6 35.7.3 72-32.8 92.3-47.6 102-74.1 131.6-96.3 154-113.7zM256 320c23.2.4 56.6-29.2 73.4-41.4 132.7-96.3 142.8-104.7 173.4-128.7 5.8-4.5 9.2-11.5 9.2-18.9v-19c0-26.5-21.5-48-48-48H48C21.5 64 0 85.5 0 112v19c0 7.4 3.4 14.3 9.2 18.9 30.6 23.9 40.7 32.4 173.4 128.7 16.8 12.2 50.2 41.8 73.4 41.4z"/></svg>email</a> or <a class="is-link" href="https://subscribe.sorryapp.com/24846f03/slack/new" target="_blank"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 448 512" class="icon filter-black" role="presentation"><path d="M94.12 315.1c0 25.9-21.16 47.06-47.06 47.06S0 341 0 315.1c0-25.9 21.16-47.06 47.06-47.06h47.06v47.06zm23.72 0c0-25.9 21.16-47.06 47.06-47.06s47.06 21.16 47.06 47.06v117.84c0 25.9-21.16 47.06-47.06 47.06s-47.06-21.16-47.06-47.06V315.1zm47.06-188.98c-25.9 0-47.06-21.16-47.06-47.06S139 32 164.9 32s47.06 21.16 47.06 47.06v47.06H164.9zm0 23.72c25.9 0 47.06 21.16 47.06 47.06s-21.16 47.06-47.06 47.06H47.06C21.16 243.96 0 222.8 0 196.9s21.16-47.06 47.06-47.06H164.9zm188.98 47.06c0-25.9 21.16-47.06 47.06-47.06 25.9 0 47.06 21.16 47.06 47.06s-21.16 47.06-47.06 47.06h-47.06V196.9zm-23.72 0c0 25.9-21.16 47.06-47.06 47.06-25.9 0-47.06-21.16-47.06-47.06V79.06c0-25.9 21.16-47.06 47.06-47.06 25.9 0 47.06 21.16 47.06 47.06V196.9zM283.1 385.88c25.9 0 47.06 21.16 47.06 47.06 0 25.9-21.16 47.06-47.06 47.06-25.9 0-47.06-21.16-47.06-47.06v-47.06h47.06zm0-23.72c-25.9 0-47.06-21.16-47.06-47.06 0-25.9 21.16-47.06 47.06-47.06h117.84c25.9 0 47.06 21.16 47.06 47.06 0 25.9-21.16 47.06-47.06 47.06H283.1z"/></svg>slack</a> </p> </li> </ul> </div> </div> </div>  </div> </footer> <script src="https://static.arxiv.org/static/base/1.0.0a5/js/member_acknowledgement.js"></script> </body> </html>

CINXE.COM

Search | arXiv e-print repository