1<!DOCTYPE html> <html> <head> <meta http-equiv="Content-Type" content="text/html; charset=UTF-8">
vendor: 64 bytes, line 1
1 <script async src="https://www.googletagmanager.com/gtag/js?id=
1G-LSGEXQZ74W
vendor: 12 bytes, line 1
1"></script>
1<script> 2
vendor: 134 bytes, lines 2-6
2window.dataLayer = window.dataLayer || []; 3 function gtag(){dataLayer.push(arguments);} 4 gtag('js', new Date()); 5 6 gtag('config', '
6G-LSGEXQZ74W
vendor: 4 bytes, line 6
6');
7</script>
7 <meta charset="utf-8"> <meta name="viewport" content="width=device-width, initial-scale=1, shrink-to-fit=no"> <meta http-equiv="X-UA-Compatible" content="IE=edge"> <title> Keisuke Sakaguchi </title> <meta name="description" content="Keisuke Sakaguchi, Associate Professor at Tohoku University. "> <link href="https://stackpath.bootstrapcdn.com/bootstrap/4.5.2/css/bootstrap.min.css" rel="stylesheet" integrity="sha512-MoRNloxbStBcD8z3M/2BmnT+rg4IsMxPkXaGh2zD6LGNNFE80W3onsAhRcMAMrSoyWL9xD7Ert0men7vR8LUZg==" crossorigin="anonymous"> <link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/mdbootstrap/4.19.1/css/mdb.min.css" integrity="sha512-RO38pBRxYH3SoOprtPTD86JFOclM51/XTIdEPh5j8sj4tp8jmQIx26twG52UaLi//hQldfrh7e51WzP9wuP32Q==" crossorigin="anonymous"> <link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/font-awesome/5.14.0/css/all.min.css" integrity="sha512-1PKOgIY59xJ8Co8+NE6FZ+LOAZKjy+KY8iq0G4B3CyeY6wYHN3yt9PW0XpSriVlkMXe40PTKnXrLnZ9+fkDaog==" crossorigin="anonymous"> <link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/academicons/1.9.0/css/academicons.min.css" integrity="sha512-W4yqoT1+8NLkinBLBZko+dFB2ZbHsYLDdr50VElllRcNt2Q4/GSs6u71UHKxB7S6JEMCp5Ve4xjh3eGQl/HRvg==" crossorigin="anonymous"> <link rel="preconnect" href="https://fonts.googleapis.com"> <link rel="preconnect" href="https://fonts.gstatic.com" crossorigin> <link href="https://fonts.googleapis.com/css2?family=Roboto:wght@300&display=swap" rel="stylesheet"> <link rel="stylesheet" href="/assets/css/github.css"> <link rel="icon" href="data:image/svg+xml,<svg%20xmlns=%22http://www.w3.org/2000/svg%22%20viewBox=%220%200%20100%20100%22><text%20y=%22.9em%22%20font-size=%2290%22>%F0%9F%92%A1</text></svg>"> <link rel="stylesheet" href="/assets/css/main.css"> <link rel="canonical" href="/">
7<script async src="https://cdn.panelbear.com/analytics.js?site=D0uh9Msel0f"></script>
7
7<script> 8 window.panelbear = window.panelbear || function() { (window.panelbear.q = window.panelbear.q || []).push(arguments); }; 9 panelbear('config', { site: 'D0uh9Msel0f' }); 10</script>
10 </head> <body class="fixed-top-nav "> <header> <nav id="navbar" class="navbar navbar-light navbar-expand-sm fixed-top"> <div class="container"> <button class="navbar-toggler collapsed ml-auto" type="button" data-toggle="collapse" data-target="#navbarNav" aria-controls="navbarNav" aria-expanded="false" aria-label="Toggle navigation"> <span class="sr-only">Toggle navigation</span> <span class="icon-bar top-bar"></span> <span class="icon-bar middle-bar"></span> <span class="icon-bar bottom-bar"></span> </button> <div class="collapse navbar-collapse text-right" id="navbarNav"> <ul class="navbar-nav ml-auto flex-nowrap"> <li class="nav-item active"> <a class="nav-link" href="/"> about <span class="sr-only">(current)</span> </a> </li> <li class="nav-item "> <a class="nav-link" href="/publications/"> publications </a> </li> <li class="nav-item "> <a class="nav-link" href="/cv/"> cv </a> </li> </ul> </div> </div> </nav> </header> <div class="container mt-5"> <div class="post"> <header class="post-header"> <h1 class="post-title"> Keisuke Sakaguchi </h1> <p class="desc">Professor @ <a href="https://cl.is.tohoku.ac.jp/" rel="external nofollow noopener" target="_blank">Tohoku University CL lab</a> (<a href="https://www.nlp.ecei.tohoku.ac.jp/" rel="external nofollow noopener" target="_blank">Tohoku NLP Group</a>).<br> Research Scientist @ <a href="https://aip.riken.jp/labs/domain_intel/nat_lang_understand/?lang=en" rel="external nofollow noopener" target="_blank">RIKEN</a></p> </header> <article> <div class="profile float-right" style="text-align: center"> <img class="img-fluid z-depth-1 rounded" src="/assets/resized/prof_pic-1400x1400.jpg" srcset=" /assets/resized/prof_pic-480x480.jpg 480w, /assets/resized/prof_pic-800x800.jpg 800w, /assets/resized/prof_pic-1400x1400.jpg 1400w,/assets/img/prof_pic.jpg 2068w"> <div class="address" style="text-align: center"> <p>keisuke.sakaguchi[at]tohoku.ac.jp</p> </div> <div class="social"> <div class="contact-icons"> <a href="https://orcid.org/0000-0002-3809-1732" title="ORCID" rel="external nofollow noopener" target="_blank"><i class="ai ai-orcid"></i></a> <a href="https://scholar.google.com/citations?user=6CRBF-MAAAAJ" title="Google Scholar" rel="external nofollow noopener" target="_blank"><i class="ai ai-google-scholar"></i></a> <a href="https://www.semanticscholar.org/author/Keisuke-Sakaguchi/2325708" title="SemanticScholar" rel="external nofollow noopener" target="_blank"><i class="ai ai-semantic-scholar"></i></a> <a href="https://github.com/keisks" title="GitHub" rel="external nofollow noopener" target="_blank"><i class="fab fa-github"></i></a> <a href="https://www.linkedin.com/in/keisks" title="LinkedIn" rel="external nofollow noopener" target="_blank"><i class="fab fa-linkedin"></i></a> <a href="https://x.com/KeisukeS_" title="X" rel="external nofollow noopener" target="_blank"><i class="fa-brands fa-x-twitter"></i></a> </div> </div> </div> <div class="clearfix"> <p>I am a professor at Tohoku University. My research interests lie at the intersection of Natural Language Processing, Machine Learning, and Psycholinguistics. My long-term research goals are</p> <ol> <li>to understand human intelligence, especially natural langauge processing, and</li> <li>to build embodied AI that is as robust and efficient as humans.</li> </ol> <p>More specifically, my research interests include: robust NLP models for noisy texts (e.g., text normalization, parsing, automated grammatical error correction), commonsense knowledge acquisition and reasoning, visual diagram understanding, NLP for educational purposes (first and second language acquisition), text generation (decoding algorithms), efficient data collection, and reliable evaluation metric design (meta-evaluation).</p> <p>For those interested in applying to our lab, please see <a href="https://keisuke-sakaguchi.github.io/admission">this information</a>.</p> </div> <div class="news"> <h2>news</h2> <div class="table-responsive"> <table class="table table-sm table-borderless"> <tr> <th scope="row">2026/08/21 Â Â Â Â </th> <td> Three papers were accepted to <strong>EMNLP</strong>. </td> </tr> <tr> <th scope="row">2026/06/17 Â Â Â Â </th> <td> The paper on Unifying Accuracy and Efficiency for Robotics Evaluation has been accepted to <strong>IROS</strong>. </td> </tr> <tr> <th scope="row">2026/04/09 Â Â Â Â </th> <td> The paper on LLMâs Bar Exam Writing Task has been accepted to <strong>ICAIL</strong>. </td> </tr> <tr> <th scope="row">2026/04/01 Â Â Â Â </th> <td> I was promoted to Professor at Tohoku University. </td> </tr> <tr> <th scope="row">2026/01/04 Â Â Â Â </th> <td> The paper on LLM CoT faithfulness has been accepted to <strong>EACL</strong>. </td> </tr> </table> <a href="/news/">previous news</a> </div> </div> </article> </div> </div> </body>
10<script src="https://cdnjs.cloudflare.com/ajax/libs/jquery/3.5.1/jquery.min.js" integrity="sha512-bLT0Qm9VnAYZDflyKcBaQ2gg0hSYNQrJ8RilYldYQ1FxQYoCLtUjuuRuZo+fjqhx/qtq/1itJ0C2ejDxltZVFg==" crossorigin="anonymous"></script>
10
10<script src="https://cdnjs.cloudflare.com/ajax/libs/popper.js/2.4.4/umd/popper.min.js" integrity="sha512-eUQ9hGdLjBjY3F41CScH3UX+4JDSI9zXeroz7hJ+RteoCaY+GP/LDoM8AO+Pt+DRFw3nXqsjh9Zsts8hnYv8/A==" crossorigin="anonymous"></script>
10
10<script src="https://stackpath.bootstrapcdn.com/bootstrap/4.5.2/js/bootstrap.min.js" integrity="sha512-M5KW3ztuIICmVIhjSqXe01oV2bpe248gOxqmlcYrEzAvws7Pw3z6BK0iGbrwvdrUQUhi3eXgtxp5I8PDo9YfjQ==" crossorigin="anonymous"></script>
10
10<script src="https://cdnjs.cloudflare.com/ajax/libs/mdbootstrap/4.19.1/js/mdb.min.js" integrity="sha512-Mug9KHKmroQFMLm93zGrjhibM2z2Obg9l6qFG2qKjXEXkMp/VDkI4uju9m4QKPjWSwQ6O2qzZEnJDEeCw0Blcw==" crossorigin="anonymous"></script>
10
10<script src="https://cdn.jsdelivr.net/npm/[email protected]/dist/medium-zoom.min.js" integrity="sha256-EdPgYcPk/IIrw7FYeuJQexva49pVRZNmt3LculEr7zM=" crossorigin="anonymous"></script>
10
10<script src="/assets/js/zoom.js"></script>
10
10<script src="/assets/js/common.js"></script>
10
10<script type="text/javascript"> 11 function play(audio_id){ 12 var audio = document.getElementById(audio_id); 13 audio.play(); 14 } 15</script>
15
15<script type="text/javascript"> 16 window.MathJax = { 17 tex: { 18 tags: 'ams' 19 } 20 }; 21</script>
21
21<script defer type="text/javascript" id="MathJax-script" src="https://cdn.jsdelivr.net/npm/[email protected]/es5/tex-mml-chtml.js"></script>
21 </html>
Line numbers count LF bytes from the start of the resource, as the search results do. Vendor segments are library code the classifier recognised; they are stored but not indexed. Bytes are shown as Latin1 characters, one per byte.