{"id":6515,"date":"2025-04-04T03:26:00","date_gmt":"2025-04-03T18:26:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=6515"},"modified":"2025-04-04T03:26:00","modified_gmt":"2025-04-03T18:26:00","slug":"claimcheck-how-grounded-are-llm-critiques-of-scientific-papers","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=6515","title":{"rendered":"CLAIMCHECK: How Grounded are LLM Critiques of Scientific Papers?"},"content":{"rendered":"\n<ul class=\"wp-block-list\">\n<li><strong>CLAIMCHECK: How Grounded are LLM Critiques of Scientific Papers?\u00a0<\/strong>[36.8]<br>CLAIMCHECK\u306f\u3001NeurIPS 2023\u30682024\u306e\u30a2\u30ce\u30c6\u30fc\u30c8\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u3067\u3042\u308a\u3001OpenReview\u304b\u3089\u62bd\u51fa\u3055\u308c\u305f\u30ec\u30d3\u30e5\u30fc\u3067\u3042\u308b\u3002 CLAIMCHECK\u306f\u3001\u30ec\u30d3\u30e5\u30fc\u306e\u5f31\u70b9\u306b\u95a2\u3059\u308bML\u306e\u5c02\u9580\u5bb6\u306b\u3088\u3063\u3066\u8c4a\u5bcc\u306a\u6ce8\u91c8\u304c\u4ed8\u3051\u3089\u308c\u3066\u304a\u308a\u3001\u8ad6\u6587\u306f\u3001\u305d\u308c\u3089\u304c\u77db\u76fe\u3057\u3066\u3044\u308b\u3068\u4e3b\u5f35\u3057\u3066\u304a\u308a\u3001\u307e\u305f\u3001\u8b58\u5225\u3055\u308c\u305f\u5f31\u70b9\u306e\u59a5\u5f53\u6027\u3001\u5ba2\u89b3\u6027\u3001\u30bf\u30a4\u30d7\u306b\u95a2\u3059\u308b\u304d\u3081\u7d30\u304b\u3044\u30e9\u30d9\u30eb\u3082\u4e3b\u5f35\u3057\u3066\u3044\u308b\u3002 \u6211\u3005\u306f,CLAIMCHECK \u304c\u652f\u63f4\u3059\u308b3\u3064\u306e\u30af\u30ec\u30fc\u30e0\u4e2d\u5fc3\u30bf\u30b9\u30af\u306b\u3064\u3044\u3066,(1) \u7d1b\u4e89\u306e\u30af\u30ec\u30fc\u30e0\u306b\u5f31\u70b9\u3092\u95a2\u9023\u4ed8\u3051\u308b\u3053\u3068,(2) \u5f31\u70b9\u306e\u304d\u3081\u7d30\u304b\u3044\u30e9\u30d9\u30eb\u3092\u4e88\u6e2c\u3057,\u305d\u306e\u7279\u7570\u6027\u3092\u9ad8\u3081\u308b\u305f\u3081\u306b\u5f31\u70b9\u3092\u66f8\u304d\u63db\u3048\u308b\u3053\u3068,(3) \u6839\u62e0\u4ed8\u304d\u63a8\u8ad6\u3067\u8ad6\u6587\u306e\u30af\u30ec\u30fc\u30e0\u3092\u691c\u8a3c\u3059\u308b\u3053\u3068,\u306e3\u3064\u306b\u3064\u3044\u3066,LCM \u3092\u30d9\u30f3\u30c1\u30de\u30fc\u30af\u3059\u308b\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2503.21717v1\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2503.21717v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Thu, 27 Mar 2025 17:29:45 GMT)<\/li>\n\n\n\n<li>\u300cThis work has introduced CLAIMCHECK\u2014a benchmark of reviewer-identified weaknesses in NeurIPS 2023 and 2024 submissions, richly annotated with descriptive labels by experts and grounded in the claims that they dispute in the reviewed papers. Further, we benchmark various LLMs on three novel tasks enabled by CLAIMCHECK\u2014Weakness Labeling and Editing (WLE), Claim Association (CA), and Claim Verification (CV)\u2014all aimed at assisting reviewers during the peer review process.\u300d\u3068\u3044\u3046\u30d9\u30f3\u30c1\u30de\u30fc\u30af\u306e\u63d0\u6848\u3002\u73fe\u5728\u306eLLM\u306b\u3068\u3063\u3066\u96e3\u3057\u3044\u30bf\u30b9\u30af\u3068\u306a\u3063\u3066\u3044\u308b\u3002<\/li>\n\n\n\n<li>\u30ea\u30dd\u30b8\u30c8\u30ea\u306f<a href=\"https:\/\/github.com\/JHU-CLSP\/CLAIMCHECK\">https:\/\/github.com\/JHU-CLSP\/CLAIMCHECK<\/a>\u3068\u306e\u3053\u3068<\/li>\n<\/ul>\n","protected":false},"excerpt":{"rendered":"","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[2],"tags":[138,491,517],"class_list":["post-6515","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-fact-checking","tag-491","tag-517"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/6515","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=6515"}],"version-history":[{"count":0,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/6515\/revisions"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=6515"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=6515"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=6515"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}