{"id":4078,"date":"2023-11-20T05:40:00","date_gmt":"2023-11-19T20:40:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=4078"},"modified":"2023-11-20T05:40:00","modified_gmt":"2023-11-19T20:40:00","slug":"factcheck-gpt","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=4078","title":{"rendered":"Factcheck-GPT"},"content":{"rendered":"\n<ul class=\"wp-block-list\">\n<li><strong>Factcheck-GPT: End-to-End Fine-Grained Document-Level Fact-Checking and Correction of LLM Output\u00a0<\/strong>[124.3]<br>\u672c\u7a3f\u3067\u306f,\u5927\u898f\u6a21\u8a00\u8a9e\u30e2\u30c7\u30eb (LLM) \u751f\u6210\u5fdc\u7b54\u306e\u4e8b\u5b9f\u6027\u306b\u6ce8\u91c8\u3092\u4ed8\u3051\u308b\u305f\u3081\u306e\u7dcf\u5408\u7684\u306a\u30a8\u30f3\u30c9\u30c4\u30fc\u30a8\u30f3\u30c9\u30bd\u30ea\u30e5\u30fc\u30b7\u30e7\u30f3\u3092\u63d0\u6848\u3059\u308b\u3002 \u30e9\u30d9\u30eb\u4ed8\u3051\u624b\u9806\u3092\u9ad8\u901f\u5316\u3057\u3001\u30e9\u30c3\u30ab\u30fc\u306e\u4f5c\u696d\u3092\u7c21\u5358\u306b\u3059\u308b\u305f\u3081\u306e\u30a2\u30ce\u30c6\u30fc\u30b7\u30e7\u30f3\u30c4\u30fc\u30eb\u3092\u8a2d\u8a08\u3057\u3001\u69cb\u7bc9\u3059\u308b\u3002 \u30aa\u30fc\u30d7\u30f3\u30c9\u30e1\u30a4\u30f3\u306e\u6587\u66f8\u30ec\u30d9\u30eb\u306e\u4e8b\u5b9f\u6027\u30d9\u30f3\u30c1\u30de\u30fc\u30af\u30923\u6bb5\u968e\u306e\u30af\u30ec\u30fc\u30e0,\u6587,\u6587\u66f8\u3067\u69cb\u7bc9\u3059\u308b\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2311.09000v1\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2311.09000v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Wed, 15 Nov 2023 14:41:57 GMT)<\/li>\n\n\n\n<li>LLM\u306e\u305f\u3081\u306e\u30d5\u30a1\u30af\u30c8\u30c1\u30a7\u30c3\u30af\u30d9\u30f3\u30c1\u30de\u30fc\u30af\uff06\u30a2\u30ce\u30c6\u30fc\u30b7\u30e7\u30f3\u30c4\u30fc\u30eb\u306e\u63d0\u6848\u3002\u300cThis reveals that current mainstreaming SOTA fact-checkers still have large room to improve on verification, particularly on false claims (F1&lt;0.53).\u300d\u3068\u306e\u3053\u3068\u3002<\/li>\n\n\n\n<li>\u30ea\u30dd\u30b8\u30c8\u30ea\u306f<a href=\"https:\/\/github.com\/yuxiaw\/Factcheck-GPT\">GitHub &#8211; yuxiaw\/Factcheck-GPT: Fact-Checking the Output of Generative Large Language Models in both Annotation and Evaluation.<\/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":[138,223],"class_list":["post-4078","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-fact-checking","tag-llm"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/4078","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=4078"}],"version-history":[{"count":0,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/4078\/revisions"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=4078"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=4078"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=4078"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}