{"id":6602,"date":"2025-04-21T04:45:00","date_gmt":"2025-04-20T19:45:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=6602"},"modified":"2025-04-21T04:45:00","modified_gmt":"2025-04-20T19:45:00","slug":"ai2-scholar-qa-organized-literature-synthesis-with-attribution-can-llms-generate-tabular-summaries-of-science-papers-rethinking-the-evaluation-protocol","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=6602","title":{"rendered":"Ai2 Scholar QA: Organized Literature Synthesis with Attribution, Can LLMs Generate Tabular Summaries of Science Papers? Rethinking the Evaluation Protocol"},"content":{"rendered":"\n<ul class=\"wp-block-list\">\n<li><strong>Ai2 Scholar QA: Organized Literature Synthesis with Attribution\u00a0<\/strong>[40.8]<br>Ai2 Scholar QA\u306f\u7121\u6599\u306e\u30aa\u30f3\u30e9\u30a4\u30f3\u79d1\u5b66\u8cea\u554f\u5fdc\u7b54\u30a2\u30d7\u30ea\u30b1\u30fc\u30b7\u30e7\u30f3\u3067\u3042\u308b\u3002 \u30ab\u30b9\u30bf\u30de\u30a4\u30ba\u53ef\u80fd\u306a\u30aa\u30fc\u30d7\u30f3\u30bd\u30fc\u30b9Python\u30d1\u30c3\u30b1\u30fc\u30b8\u3068\u3057\u3066\u3001\u30a4\u30f3\u30bf\u30e9\u30af\u30c6\u30a3\u30d6\u306aWeb\u30a2\u30d7\u30ea\u3068\u3057\u3066\u3001\u30d1\u30a4\u30d7\u30e9\u30a4\u30f3\u5168\u4f53\u3092\u516c\u958b\u3057\u3066\u3044\u307e\u3059\u3002 \u6700\u8fd1\u306e\u79d1\u5b66\u7684QA\u30d9\u30f3\u30c1\u30de\u30fc\u30af\u3067\u306f\u3001Ai2 Scholar QA\u304c\u7af6\u5408\u3059\u308b\u30b7\u30b9\u30c6\u30e0\u3088\u308a\u512a\u308c\u3066\u3044\u308b\u3053\u3068\u304c\u5224\u660e\u3057\u305f\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2504.10861v1\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2504.10861v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Tue, 15 Apr 2025 04:48:18 GMT)<\/li>\n\n\n\n<li>\u300cwe introduce Ai2 Scholar QA, a free-to-use scientific QA system (qa.allen.ai), and share our key components as open source software and public APIs.\u300d\u3068\u3044\u3046\u79d1\u5b66\u306b\u95a2\u3059\u308b\u8cea\u554f\u3078\u306e\u30ec\u30dd\u30fc\u30c8\u3092\u751f\u6210\u3059\u308bOSS\u5b9f\u88c5<\/li>\n<\/ul>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>Can LLMs Generate Tabular Summaries of Science Papers? Rethinking the Evaluation Protocol\u00a0<\/strong>[83.9]<br>\u6587\u732e\u30ec\u30d3\u30e5\u30fc\u8868\u306f\u3001\u79d1\u5b66\u8ad6\u6587\u306e\u96c6\u5408\u3092\u8981\u7d04\u3057\u6bd4\u8f03\u3059\u308b\u305f\u3081\u306b\u6b20\u304b\u305b\u306a\u3044\u3082\u306e\u3067\u3042\u308b\u3002 \u5b66\u8853\u8ad6\u6587\u306e\u53ce\u96c6\u306b\u3042\u305f\u308a,\u30e6\u30fc\u30b6\u306e\u60c5\u5831\u30cb\u30fc\u30ba\u3092\u6700\u5927\u9650\u306b\u6e80\u305f\u3059\u8868\u3092\u4f5c\u6210\u3059\u308b\u30bf\u30b9\u30af\u306b\u3064\u3044\u3066\u691c\u8a0e\u3059\u308b\u3002 \u6211\u3005\u306e\u8ca2\u732e\u306f\u3001\u73fe\u5b9f\u4e16\u754c\u3067\u906d\u9047\u3059\u308b3\u3064\u306e\u91cd\u8981\u306a\u8ab2\u984c\u306b\u7126\u70b9\u3092\u5f53\u3066\u3066\u3044\u308b: (i)\u30e6\u30fc\u30b6\u30fc\u30d7\u30ed\u30f3\u30d7\u30c8\u306f\u3001\u3057\u3070\u3057\u3070\u672a\u7279\u5b9a\u3067\u3042\u308b; (ii)\u691c\u7d22\u3055\u308c\u305f\u5019\u88dc\u8ad6\u6587\u306f\u3001\u3057\u3070\u3057\u3070\u7121\u95a2\u4fc2\u306a\u5185\u5bb9\u3092\u542b\u3080; (iii)\u30bf\u30b9\u30af\u8a55\u4fa1\u306f\u3001\u6d45\u3044\u30c6\u30ad\u30b9\u30c8\u985e\u4f3c\u6027\u6280\u8853\u3092\u8d85\u3048\u3066\u9032\u3080\u3079\u304d\u3067\u3042\u308b\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2504.10284v1\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2504.10284v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Mon, 14 Apr 2025 14:52:28 GMT)<\/li>\n\n\n\n<li>\u3053\u3061\u3089\u306f\u6587\u732e\u30ec\u30d3\u30e5\u30fc\u8868\u3092\u4f5c\u6210\u3059\u308b\u7814\u7a76\u3001\u6bd4\u8f03\u691c\u8a3c\u3092\u884c\u3046\u4e0a\u3067\u91cd\u8981\u306a\u30bf\u30b9\u30af\u3002\u6700\u8fd1\u306eLLM\u3067\u3042\u308c\u3070\u89e3\u3051\u305d\u3046\u306a\u30bf\u30b9\u30af\u306b\u898b\u3048\u3066\u30b7\u30f3\u30d7\u30eb\u306a\u65b9\u91dd\u3067\u306f\u610f\u5916\u3068\u3046\u307e\u304f\u3044\u304b\u306a\u3044\u3088\u3046\u3002<\/li>\n\n\n\n<li>\u30ea\u30dd\u30b8\u30c8\u30ea\u306f<a href=\"https:\/\/github.com\/JHU-CLSP\/arXiv2Table\">GitHub &#8211; JHU-CLSP\/arXiv2Table<\/a><\/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":[293,623],"class_list":["post-6602","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-oss","tag-623"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/6602","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=6602"}],"version-history":[{"count":0,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/6602\/revisions"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=6602"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=6602"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=6602"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}