CINXE.COM

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"/> <!-- new favicon config and versions by realfavicongenerator.net --> <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"> <!-- end favicon config --> <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> <!-- contains Cornell logo and sponsor statement --> <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> <!-- contains arXiv identity and search bar --> <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> <!-- closes identity --> <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&ndash;8 of 8 results for author: <span class="mathjax">Kambadur, M</span> </h1> </div> <div class="level-right is-hidden-mobile"> <!-- feedback for mobile is moved to footer --> <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>&nbsp;&nbsp;</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&amp;query=Kambadur%2C+M">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="Kambadur, M"> </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=Kambadur%2C+M&amp;terms-0-field=author&amp;size=50&amp;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="Kambadur, M"> <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> <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/2410.15553">arXiv:2410.15553</a> <span>&nbsp;[<a href="https://arxiv.org/pdf/2410.15553">pdf</a>, <a href="https://arxiv.org/format/2410.15553">other</a>]&nbsp;</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-IF: Benchmarking LLMs on Multi-Turn and Multilingual Instructions Following </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&amp;query=He%2C+Y">Yun He</a>, <a href="/search/cs?searchtype=author&amp;query=Jin%2C+D">Di Jin</a>, <a href="/search/cs?searchtype=author&amp;query=Wang%2C+C">Chaoqi Wang</a>, <a href="/search/cs?searchtype=author&amp;query=Bi%2C+C">Chloe Bi</a>, <a href="/search/cs?searchtype=author&amp;query=Mandyam%2C+K">Karishma Mandyam</a>, <a href="/search/cs?searchtype=author&amp;query=Zhang%2C+H">Hejia Zhang</a>, <a href="/search/cs?searchtype=author&amp;query=Zhu%2C+C">Chen Zhu</a>, <a href="/search/cs?searchtype=author&amp;query=Li%2C+N">Ning Li</a>, <a href="/search/cs?searchtype=author&amp;query=Xu%2C+T">Tengyu Xu</a>, <a href="/search/cs?searchtype=author&amp;query=Lv%2C+H">Hongjiang Lv</a>, <a href="/search/cs?searchtype=author&amp;query=Bhosale%2C+S">Shruti Bhosale</a>, <a href="/search/cs?searchtype=author&amp;query=Zhu%2C+C">Chenguang Zhu</a>, <a href="/search/cs?searchtype=author&amp;query=Sankararaman%2C+K+A">Karthik Abinav Sankararaman</a>, <a href="/search/cs?searchtype=author&amp;query=Helenowski%2C+E">Eryk Helenowski</a>, <a href="/search/cs?searchtype=author&amp;query=Kambadur%2C+M">Melanie Kambadur</a>, <a href="/search/cs?searchtype=author&amp;query=Tayade%2C+A">Aditya Tayade</a>, <a href="/search/cs?searchtype=author&amp;query=Ma%2C+H">Hao Ma</a>, <a href="/search/cs?searchtype=author&amp;query=Fang%2C+H">Han Fang</a>, <a href="/search/cs?searchtype=author&amp;query=Wang%2C+S">Sinong 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="2410.15553v2-abstract-short" style="display: inline;"> Large Language Models (LLMs) have demonstrated impressive capabilities in various tasks, including instruction following, which is crucial for aligning model outputs with user expectations. However, evaluating LLMs&#39; ability to follow instructions remains challenging due to the complexity and subjectivity of human language. Current benchmarks primarily focus on single-turn, monolingual instructions&hellip; <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.15553v2-abstract-full').style.display = 'inline'; document.getElementById('2410.15553v2-abstract-short').style.display = 'none';">&#9661; More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.15553v2-abstract-full" style="display: none;"> Large Language Models (LLMs) have demonstrated impressive capabilities in various tasks, including instruction following, which is crucial for aligning model outputs with user expectations. However, evaluating LLMs&#39; ability to follow instructions remains challenging due to the complexity and subjectivity of human language. Current benchmarks primarily focus on single-turn, monolingual instructions, which do not adequately reflect the complexities of real-world applications that require handling multi-turn and multilingual interactions. To address this gap, we introduce Multi-IF, a new benchmark designed to assess LLMs&#39; proficiency in following multi-turn and multilingual instructions. Multi-IF, which utilizes a hybrid framework combining LLM and human annotators, expands upon the IFEval by incorporating multi-turn sequences and translating the English prompts into another 7 languages, resulting in a dataset of 4,501 multilingual conversations, where each has three turns. Our evaluation of 14 state-of-the-art LLMs on Multi-IF reveals that it presents a significantly more challenging task than existing benchmarks. All the models tested showed a higher rate of failure in executing instructions correctly with each additional turn. For example, o1-preview drops from 0.877 at the first turn to 0.707 at the third turn in terms of average accuracy over all languages. Moreover, languages with non-Latin scripts (Hindi, Russian, and Chinese) generally exhibit higher error rates, suggesting potential limitations in the models&#39; multilingual capabilities. We release Multi-IF prompts and the evaluation code base to encourage further research in this critical area. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.15553v2-abstract-full').style.display = 'none'; document.getElementById('2410.15553v2-abstract-short').style.display = 'inline';">&#9651; Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 12 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 20 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/2409.19951">arXiv:2409.19951</a> <span>&nbsp;[<a href="https://arxiv.org/pdf/2409.19951">pdf</a>, <a href="https://arxiv.org/format/2409.19951">other</a>]&nbsp;</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="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> </div> </div> <p class="title is-5 mathjax"> Law of the Weakest Link: Cross Capabilities of Large Language Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&amp;query=Zhong%2C+M">Ming Zhong</a>, <a href="/search/cs?searchtype=author&amp;query=Zhang%2C+A">Aston Zhang</a>, <a href="/search/cs?searchtype=author&amp;query=Wang%2C+X">Xuewei Wang</a>, <a href="/search/cs?searchtype=author&amp;query=Hou%2C+R">Rui Hou</a>, <a href="/search/cs?searchtype=author&amp;query=Xiong%2C+W">Wenhan Xiong</a>, <a href="/search/cs?searchtype=author&amp;query=Zhu%2C+C">Chenguang Zhu</a>, <a href="/search/cs?searchtype=author&amp;query=Chen%2C+Z">Zhengxing Chen</a>, <a href="/search/cs?searchtype=author&amp;query=Tan%2C+L">Liang Tan</a>, <a href="/search/cs?searchtype=author&amp;query=Bi%2C+C">Chloe Bi</a>, <a href="/search/cs?searchtype=author&amp;query=Lewis%2C+M">Mike Lewis</a>, <a href="/search/cs?searchtype=author&amp;query=Popuri%2C+S">Sravya Popuri</a>, <a href="/search/cs?searchtype=author&amp;query=Narang%2C+S">Sharan Narang</a>, <a href="/search/cs?searchtype=author&amp;query=Kambadur%2C+M">Melanie Kambadur</a>, <a href="/search/cs?searchtype=author&amp;query=Mahajan%2C+D">Dhruv Mahajan</a>, <a href="/search/cs?searchtype=author&amp;query=Edunov%2C+S">Sergey Edunov</a>, <a href="/search/cs?searchtype=author&amp;query=Han%2C+J">Jiawei Han</a>, <a href="/search/cs?searchtype=author&amp;query=van+der+Maaten%2C+L">Laurens van der Maaten</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="2409.19951v2-abstract-short" style="display: inline;"> The development and evaluation of Large Language Models (LLMs) have largely focused on individual capabilities. However, this overlooks the intersection of multiple abilities across different types of expertise that are often required for real-world tasks, which we term cross capabilities. To systematically explore this concept, we first define seven core individual capabilities and then pair them&hellip; <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.19951v2-abstract-full').style.display = 'inline'; document.getElementById('2409.19951v2-abstract-short').style.display = 'none';">&#9661; More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.19951v2-abstract-full" style="display: none;"> The development and evaluation of Large Language Models (LLMs) have largely focused on individual capabilities. However, this overlooks the intersection of multiple abilities across different types of expertise that are often required for real-world tasks, which we term cross capabilities. To systematically explore this concept, we first define seven core individual capabilities and then pair them to form seven common cross capabilities, each supported by a manually constructed taxonomy. Building on these definitions, we introduce CrossEval, a benchmark comprising 1,400 human-annotated prompts, with 100 prompts for each individual and cross capability. To ensure reliable evaluation, we involve expert annotators to assess 4,200 model responses, gathering 8,400 human ratings with detailed explanations to serve as reference examples. Our findings reveal that, in both static evaluations and attempts to enhance specific abilities, current LLMs consistently exhibit the &#34;Law of the Weakest Link,&#34; where cross-capability performance is significantly constrained by the weakest component. Specifically, across 58 cross-capability scores from 17 models, 38 scores are lower than all individual capabilities, while 20 fall between strong and weak, but closer to the weaker ability. These results highlight the under-performance of LLMs in cross-capability tasks, making the identification and improvement of the weakest capabilities a critical priority for future research to optimize performance in complex, multi-dimensional scenarios. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.19951v2-abstract-full').style.display = 'none'; document.getElementById('2409.19951v2-abstract-short').style.display = 'inline';">&#9651; Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 2 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 30 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">Data, Code, &amp; Benchmark: www.llm-cross-capabilities.org</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2407.21783">arXiv:2407.21783</a> <span>&nbsp;[<a href="https://arxiv.org/pdf/2407.21783">pdf</a>, <a href="https://arxiv.org/format/2407.21783">other</a>]&nbsp;</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="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> </div> </div> <p class="title is-5 mathjax"> The Llama 3 Herd of Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&amp;query=Dubey%2C+A">Abhimanyu Dubey</a>, <a href="/search/cs?searchtype=author&amp;query=Jauhri%2C+A">Abhinav Jauhri</a>, <a href="/search/cs?searchtype=author&amp;query=Pandey%2C+A">Abhinav Pandey</a>, <a href="/search/cs?searchtype=author&amp;query=Kadian%2C+A">Abhishek Kadian</a>, <a href="/search/cs?searchtype=author&amp;query=Al-Dahle%2C+A">Ahmad Al-Dahle</a>, <a href="/search/cs?searchtype=author&amp;query=Letman%2C+A">Aiesha Letman</a>, <a href="/search/cs?searchtype=author&amp;query=Mathur%2C+A">Akhil Mathur</a>, <a href="/search/cs?searchtype=author&amp;query=Schelten%2C+A">Alan Schelten</a>, <a href="/search/cs?searchtype=author&amp;query=Yang%2C+A">Amy Yang</a>, <a href="/search/cs?searchtype=author&amp;query=Fan%2C+A">Angela Fan</a>, <a href="/search/cs?searchtype=author&amp;query=Goyal%2C+A">Anirudh Goyal</a>, <a href="/search/cs?searchtype=author&amp;query=Hartshorn%2C+A">Anthony Hartshorn</a>, <a href="/search/cs?searchtype=author&amp;query=Yang%2C+A">Aobo Yang</a>, <a href="/search/cs?searchtype=author&amp;query=Mitra%2C+A">Archi Mitra</a>, <a href="/search/cs?searchtype=author&amp;query=Sravankumar%2C+A">Archie Sravankumar</a>, <a href="/search/cs?searchtype=author&amp;query=Korenev%2C+A">Artem Korenev</a>, <a href="/search/cs?searchtype=author&amp;query=Hinsvark%2C+A">Arthur Hinsvark</a>, <a href="/search/cs?searchtype=author&amp;query=Rao%2C+A">Arun Rao</a>, <a href="/search/cs?searchtype=author&amp;query=Zhang%2C+A">Aston Zhang</a>, <a href="/search/cs?searchtype=author&amp;query=Rodriguez%2C+A">Aurelien Rodriguez</a>, <a href="/search/cs?searchtype=author&amp;query=Gregerson%2C+A">Austen Gregerson</a>, <a href="/search/cs?searchtype=author&amp;query=Spataru%2C+A">Ava Spataru</a>, <a href="/search/cs?searchtype=author&amp;query=Roziere%2C+B">Baptiste Roziere</a>, <a href="/search/cs?searchtype=author&amp;query=Biron%2C+B">Bethany Biron</a>, <a href="/search/cs?searchtype=author&amp;query=Tang%2C+B">Binh Tang</a> , et al. (510 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="2407.21783v2-abstract-short" style="display: inline;"> Modern artificial intelligence (AI) systems are powered by foundation models. This paper presents a new set of foundation models, called Llama 3. It is a herd of language models that natively support multilinguality, coding, reasoning, and tool usage. Our largest model is a dense Transformer with 405B parameters and a context window of up to 128K tokens. This paper presents an extensive empirical&hellip; <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.21783v2-abstract-full').style.display = 'inline'; document.getElementById('2407.21783v2-abstract-short').style.display = 'none';">&#9661; More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.21783v2-abstract-full" style="display: none;"> Modern artificial intelligence (AI) systems are powered by foundation models. This paper presents a new set of foundation models, called Llama 3. It is a herd of language models that natively support multilinguality, coding, reasoning, and tool usage. Our largest model is a dense Transformer with 405B parameters and a context window of up to 128K tokens. This paper presents an extensive empirical evaluation of Llama 3. We find that Llama 3 delivers comparable quality to leading language models such as GPT-4 on a plethora of tasks. We publicly release Llama 3, including pre-trained and post-trained versions of the 405B parameter language model and our Llama Guard 3 model for input and output safety. The paper also presents the results of experiments in which we integrate image, video, and speech capabilities into Llama 3 via a compositional approach. We observe this approach performs competitively with the state-of-the-art on image, video, and speech recognition tasks. The resulting models are not yet being broadly released as they are still under development. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.21783v2-abstract-full').style.display = 'none'; document.getElementById('2407.21783v2-abstract-short').style.display = 'inline';">&#9651; Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 15 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 31 July, 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/2307.09288">arXiv:2307.09288</a> <span>&nbsp;[<a href="https://arxiv.org/pdf/2307.09288">pdf</a>, <a href="https://arxiv.org/format/2307.09288">other</a>]&nbsp;</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"> Llama 2: Open Foundation and Fine-Tuned Chat Models </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&amp;query=Touvron%2C+H">Hugo Touvron</a>, <a href="/search/cs?searchtype=author&amp;query=Martin%2C+L">Louis Martin</a>, <a href="/search/cs?searchtype=author&amp;query=Stone%2C+K">Kevin Stone</a>, <a href="/search/cs?searchtype=author&amp;query=Albert%2C+P">Peter Albert</a>, <a href="/search/cs?searchtype=author&amp;query=Almahairi%2C+A">Amjad Almahairi</a>, <a href="/search/cs?searchtype=author&amp;query=Babaei%2C+Y">Yasmine Babaei</a>, <a href="/search/cs?searchtype=author&amp;query=Bashlykov%2C+N">Nikolay Bashlykov</a>, <a href="/search/cs?searchtype=author&amp;query=Batra%2C+S">Soumya Batra</a>, <a href="/search/cs?searchtype=author&amp;query=Bhargava%2C+P">Prajjwal Bhargava</a>, <a href="/search/cs?searchtype=author&amp;query=Bhosale%2C+S">Shruti Bhosale</a>, <a href="/search/cs?searchtype=author&amp;query=Bikel%2C+D">Dan Bikel</a>, <a href="/search/cs?searchtype=author&amp;query=Blecher%2C+L">Lukas Blecher</a>, <a href="/search/cs?searchtype=author&amp;query=Ferrer%2C+C+C">Cristian Canton Ferrer</a>, <a href="/search/cs?searchtype=author&amp;query=Chen%2C+M">Moya Chen</a>, <a href="/search/cs?searchtype=author&amp;query=Cucurull%2C+G">Guillem Cucurull</a>, <a href="/search/cs?searchtype=author&amp;query=Esiobu%2C+D">David Esiobu</a>, <a href="/search/cs?searchtype=author&amp;query=Fernandes%2C+J">Jude Fernandes</a>, <a href="/search/cs?searchtype=author&amp;query=Fu%2C+J">Jeremy Fu</a>, <a href="/search/cs?searchtype=author&amp;query=Fu%2C+W">Wenyin Fu</a>, <a href="/search/cs?searchtype=author&amp;query=Fuller%2C+B">Brian Fuller</a>, <a href="/search/cs?searchtype=author&amp;query=Gao%2C+C">Cynthia Gao</a>, <a href="/search/cs?searchtype=author&amp;query=Goswami%2C+V">Vedanuj Goswami</a>, <a href="/search/cs?searchtype=author&amp;query=Goyal%2C+N">Naman Goyal</a>, <a href="/search/cs?searchtype=author&amp;query=Hartshorn%2C+A">Anthony Hartshorn</a>, <a href="/search/cs?searchtype=author&amp;query=Hosseini%2C+S">Saghar Hosseini</a> , et al. (43 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="2307.09288v2-abstract-short" style="display: inline;"> In this work, we develop and release Llama 2, a collection of pretrained and fine-tuned large language models (LLMs) ranging in scale from 7 billion to 70 billion parameters. Our fine-tuned LLMs, called Llama 2-Chat, are optimized for dialogue use cases. Our models outperform open-source chat models on most benchmarks we tested, and based on our human evaluations for helpfulness and safety, may be&hellip; <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2307.09288v2-abstract-full').style.display = 'inline'; document.getElementById('2307.09288v2-abstract-short').style.display = 'none';">&#9661; More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2307.09288v2-abstract-full" style="display: none;"> In this work, we develop and release Llama 2, a collection of pretrained and fine-tuned large language models (LLMs) ranging in scale from 7 billion to 70 billion parameters. Our fine-tuned LLMs, called Llama 2-Chat, are optimized for dialogue use cases. Our models outperform open-source chat models on most benchmarks we tested, and based on our human evaluations for helpfulness and safety, may be a suitable substitute for closed-source models. We provide a detailed description of our approach to fine-tuning and safety improvements of Llama 2-Chat in order to enable the community to build on our work and contribute to the responsible development of LLMs. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2307.09288v2-abstract-full').style.display = 'none'; document.getElementById('2307.09288v2-abstract-short').style.display = 'inline';">&#9651; Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 19 July, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 18 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/2306.04765">arXiv:2306.04765</a> <span>&nbsp;[<a href="https://arxiv.org/pdf/2306.04765">pdf</a>, <a href="https://arxiv.org/format/2306.04765">other</a>]&nbsp;</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="Computation and Language">cs.CL</span> </div> </div> <p class="title is-5 mathjax"> The HCI Aspects of Public Deployment of Research Chatbots: A User Study, Design Recommendations, and Open Challenges </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&amp;query=Behrooz%2C+M">Morteza Behrooz</a>, <a href="/search/cs?searchtype=author&amp;query=Ngan%2C+W">William Ngan</a>, <a href="/search/cs?searchtype=author&amp;query=Lane%2C+J">Joshua Lane</a>, <a href="/search/cs?searchtype=author&amp;query=Morse%2C+G">Giuliano Morse</a>, <a href="/search/cs?searchtype=author&amp;query=Babcock%2C+B">Benjamin Babcock</a>, <a href="/search/cs?searchtype=author&amp;query=Shuster%2C+K">Kurt Shuster</a>, <a href="/search/cs?searchtype=author&amp;query=Komeili%2C+M">Mojtaba Komeili</a>, <a href="/search/cs?searchtype=author&amp;query=Chen%2C+M">Moya Chen</a>, <a href="/search/cs?searchtype=author&amp;query=Kambadur%2C+M">Melanie Kambadur</a>, <a href="/search/cs?searchtype=author&amp;query=Boureau%2C+Y">Y-Lan Boureau</a>, <a href="/search/cs?searchtype=author&amp;query=Weston%2C+J">Jason Weston</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="2306.04765v1-abstract-short" style="display: inline;"> Publicly deploying research chatbots is a nuanced topic involving necessary risk-benefit analyses. While there have recently been frequent discussions on whether it is responsible to deploy such models, there has been far less focus on the interaction paradigms and design approaches that the resulting interfaces should adopt, in order to achieve their goals more effectively. We aim to pose, ground&hellip; <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2306.04765v1-abstract-full').style.display = 'inline'; document.getElementById('2306.04765v1-abstract-short').style.display = 'none';">&#9661; More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2306.04765v1-abstract-full" style="display: none;"> Publicly deploying research chatbots is a nuanced topic involving necessary risk-benefit analyses. While there have recently been frequent discussions on whether it is responsible to deploy such models, there has been far less focus on the interaction paradigms and design approaches that the resulting interfaces should adopt, in order to achieve their goals more effectively. We aim to pose, ground, and attempt to answer HCI questions involved in this scope, by reporting on a mixed-methods user study conducted on a recent research chatbot. We find that abstract anthropomorphic representation for the agent has a significant effect on user&#39;s perception, that offering AI explainability may have an impact on feedback rates, and that two (diegetic and extradiegetic) levels of the chat experience should be intentionally designed. We offer design recommendations and areas of further focus for the research community. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2306.04765v1-abstract-full').style.display = 'none'; document.getElementById('2306.04765v1-abstract-short').style.display = 'inline';">&#9651; Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 7 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/2304.09871">arXiv:2304.09871</a> <span>&nbsp;[<a href="https://arxiv.org/pdf/2304.09871">pdf</a>, <a href="https://arxiv.org/format/2304.09871">other</a>]&nbsp;</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="Optimization and Control">math.OC</span> </div> </div> <p class="title is-5 mathjax"> A Theory on Adam Instability in Large-Scale Machine Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&amp;query=Molybog%2C+I">Igor Molybog</a>, <a href="/search/cs?searchtype=author&amp;query=Albert%2C+P">Peter Albert</a>, <a href="/search/cs?searchtype=author&amp;query=Chen%2C+M">Moya Chen</a>, <a href="/search/cs?searchtype=author&amp;query=DeVito%2C+Z">Zachary DeVito</a>, <a href="/search/cs?searchtype=author&amp;query=Esiobu%2C+D">David Esiobu</a>, <a href="/search/cs?searchtype=author&amp;query=Goyal%2C+N">Naman Goyal</a>, <a href="/search/cs?searchtype=author&amp;query=Koura%2C+P+S">Punit Singh Koura</a>, <a href="/search/cs?searchtype=author&amp;query=Narang%2C+S">Sharan Narang</a>, <a href="/search/cs?searchtype=author&amp;query=Poulton%2C+A">Andrew Poulton</a>, <a href="/search/cs?searchtype=author&amp;query=Silva%2C+R">Ruan Silva</a>, <a href="/search/cs?searchtype=author&amp;query=Tang%2C+B">Binh Tang</a>, <a href="/search/cs?searchtype=author&amp;query=Liskovich%2C+D">Diana Liskovich</a>, <a href="/search/cs?searchtype=author&amp;query=Xu%2C+P">Puxin Xu</a>, <a href="/search/cs?searchtype=author&amp;query=Zhang%2C+Y">Yuchen Zhang</a>, <a href="/search/cs?searchtype=author&amp;query=Kambadur%2C+M">Melanie Kambadur</a>, <a href="/search/cs?searchtype=author&amp;query=Roller%2C+S">Stephen Roller</a>, <a href="/search/cs?searchtype=author&amp;query=Zhang%2C+S">Susan 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="2304.09871v2-abstract-short" style="display: inline;"> We present a theory for the previously unexplained divergent behavior noticed in the training of large language models. We argue that the phenomenon is an artifact of the dominant optimization algorithm used for training, called Adam. We observe that Adam can enter a state in which the parameter update vector has a relatively large norm and is essentially uncorrelated with the direction of descent&hellip; <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2304.09871v2-abstract-full').style.display = 'inline'; document.getElementById('2304.09871v2-abstract-short').style.display = 'none';">&#9661; More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2304.09871v2-abstract-full" style="display: none;"> We present a theory for the previously unexplained divergent behavior noticed in the training of large language models. We argue that the phenomenon is an artifact of the dominant optimization algorithm used for training, called Adam. We observe that Adam can enter a state in which the parameter update vector has a relatively large norm and is essentially uncorrelated with the direction of descent on the training loss landscape, leading to divergence. This artifact is more likely to be observed in the training of a deep model with a large batch size, which is the typical setting of large-scale language model training. To argue the theory, we present observations from the training runs of the language models of different scales: 7 billion, 30 billion, 65 billion, and 546 billion parameters. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2304.09871v2-abstract-full').style.display = 'none'; document.getElementById('2304.09871v2-abstract-short').style.display = 'inline';">&#9651; Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 25 April, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 19 April, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2208.03188">arXiv:2208.03188</a> <span>&nbsp;[<a href="https://arxiv.org/pdf/2208.03188">pdf</a>, <a href="https://arxiv.org/format/2208.03188">other</a>]&nbsp;</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"> BlenderBot 3: a deployed conversational agent that continually learns to responsibly engage </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&amp;query=Shuster%2C+K">Kurt Shuster</a>, <a href="/search/cs?searchtype=author&amp;query=Xu%2C+J">Jing Xu</a>, <a href="/search/cs?searchtype=author&amp;query=Komeili%2C+M">Mojtaba Komeili</a>, <a href="/search/cs?searchtype=author&amp;query=Ju%2C+D">Da Ju</a>, <a href="/search/cs?searchtype=author&amp;query=Smith%2C+E+M">Eric Michael Smith</a>, <a href="/search/cs?searchtype=author&amp;query=Roller%2C+S">Stephen Roller</a>, <a href="/search/cs?searchtype=author&amp;query=Ung%2C+M">Megan Ung</a>, <a href="/search/cs?searchtype=author&amp;query=Chen%2C+M">Moya Chen</a>, <a href="/search/cs?searchtype=author&amp;query=Arora%2C+K">Kushal Arora</a>, <a href="/search/cs?searchtype=author&amp;query=Lane%2C+J">Joshua Lane</a>, <a href="/search/cs?searchtype=author&amp;query=Behrooz%2C+M">Morteza Behrooz</a>, <a href="/search/cs?searchtype=author&amp;query=Ngan%2C+W">William Ngan</a>, <a href="/search/cs?searchtype=author&amp;query=Poff%2C+S">Spencer Poff</a>, <a href="/search/cs?searchtype=author&amp;query=Goyal%2C+N">Naman Goyal</a>, <a href="/search/cs?searchtype=author&amp;query=Szlam%2C+A">Arthur Szlam</a>, <a href="/search/cs?searchtype=author&amp;query=Boureau%2C+Y">Y-Lan Boureau</a>, <a href="/search/cs?searchtype=author&amp;query=Kambadur%2C+M">Melanie Kambadur</a>, <a href="/search/cs?searchtype=author&amp;query=Weston%2C+J">Jason Weston</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="2208.03188v3-abstract-short" style="display: inline;"> We present BlenderBot 3, a 175B parameter dialogue model capable of open-domain conversation with access to the internet and a long-term memory, and having been trained on a large number of user defined tasks. We release both the model weights and code, and have also deployed the model on a public web page to interact with organic users. This technical report describes how the model was built (arc&hellip; <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2208.03188v3-abstract-full').style.display = 'inline'; document.getElementById('2208.03188v3-abstract-short').style.display = 'none';">&#9661; More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2208.03188v3-abstract-full" style="display: none;"> We present BlenderBot 3, a 175B parameter dialogue model capable of open-domain conversation with access to the internet and a long-term memory, and having been trained on a large number of user defined tasks. We release both the model weights and code, and have also deployed the model on a public web page to interact with organic users. This technical report describes how the model was built (architecture, model and training scheme), and details of its deployment, including safety mechanisms. Human evaluations show its superiority to existing open-domain dialogue agents, including its predecessors (Roller et al., 2021; Komeili et al., 2022). Finally, we detail our plan for continual learning using the data collected from deployment, which will also be publicly released. The goal of this research program is thus to enable the community to study ever-improving responsible agents that learn through interaction. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2208.03188v3-abstract-full').style.display = 'none'; document.getElementById('2208.03188v3-abstract-short').style.display = 'inline';">&#9651; Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 10 August, 2022; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 5 August, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2022. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2205.09209">arXiv:2205.09209</a> <span>&nbsp;[<a href="https://arxiv.org/pdf/2205.09209">pdf</a>, <a href="https://arxiv.org/format/2205.09209">other</a>]&nbsp;</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="Computers and Society">cs.CY</span> </div> </div> <p class="title is-5 mathjax"> &#34;I&#39;m sorry to hear that&#34;: Finding New Biases in Language Models with a Holistic Descriptor Dataset </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/cs?searchtype=author&amp;query=Smith%2C+E+M">Eric Michael Smith</a>, <a href="/search/cs?searchtype=author&amp;query=Hall%2C+M">Melissa Hall</a>, <a href="/search/cs?searchtype=author&amp;query=Kambadur%2C+M">Melanie Kambadur</a>, <a href="/search/cs?searchtype=author&amp;query=Presani%2C+E">Eleonora Presani</a>, <a href="/search/cs?searchtype=author&amp;query=Williams%2C+A">Adina Williams</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="2205.09209v2-abstract-short" style="display: inline;"> As language models grow in popularity, it becomes increasingly important to clearly measure all possible markers of demographic identity in order to avoid perpetuating existing societal harms. Many datasets for measuring bias currently exist, but they are restricted in their coverage of demographic axes and are commonly used with preset bias tests that presuppose which types of biases models can e&hellip; <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2205.09209v2-abstract-full').style.display = 'inline'; document.getElementById('2205.09209v2-abstract-short').style.display = 'none';">&#9661; More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2205.09209v2-abstract-full" style="display: none;"> As language models grow in popularity, it becomes increasingly important to clearly measure all possible markers of demographic identity in order to avoid perpetuating existing societal harms. Many datasets for measuring bias currently exist, but they are restricted in their coverage of demographic axes and are commonly used with preset bias tests that presuppose which types of biases models can exhibit. In this work, we present a new, more inclusive bias measurement dataset, HolisticBias, which includes nearly 600 descriptor terms across 13 different demographic axes. HolisticBias was assembled in a participatory process including experts and community members with lived experience of these terms. These descriptors combine with a set of bias measurement templates to produce over 450,000 unique sentence prompts, which we use to explore, identify, and reduce novel forms of bias in several generative models. We demonstrate that HolisticBias is effective at measuring previously undetectable biases in token likelihoods from language models, as well as in an offensiveness classifier. We will invite additions and amendments to the dataset, which we hope will serve as a basis for more easy-to-use and standardized methods for evaluating bias in NLP models. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2205.09209v2-abstract-full').style.display = 'none'; document.getElementById('2205.09209v2-abstract-short').style.display = 'inline';">&#9651; Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 27 October, 2022; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 18 May, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2022. </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">EMNLP 2022</span> </p> </li> </ol> <div class="is-hidden-tablet"> <!-- feedback for mobile only --> <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>&nbsp;&nbsp;</span> </div> </div> </main> <footer> <div class="columns is-desktop" role="navigation" aria-label="Secondary"> <!-- MetaColumn 1 --> <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> <!-- end MetaColumn 1 --> <!-- MetaColumn 2 --> <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> <!-- end MetaColumn 2 --> </div> </footer> <script src="https://static.arxiv.org/static/base/1.0.0a5/js/member_acknowledgement.js"></script> </body> </html>

Pages: 1 2 3 4 5 6 7 8 9 10