{"id":3919,"date":"2023-10-26T05:46:00","date_gmt":"2023-10-25T20:46:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=3919"},"modified":"2023-10-26T05:46:00","modified_gmt":"2023-10-25T20:46:00","slug":"felm-factuality-evaluation-of-large-language-models","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=3919","title":{"rendered":"FELM: Factuality Evaluation of large Language Models"},"content":{"rendered":"\n<ul class=\"wp-block-list\">\n<li><strong>FELM: Benchmarking Factuality Evaluation of Large Language Models&nbsp;<\/strong>[40.8]<br>\u672c\u7a3f\u3067\u306f,Felm\u3068\u547c\u3070\u308c\u308b\u5927\u898f\u6a21\u8a00\u8a9e\u30e2\u30c7\u30eb\u306e\u30d5\u30a1\u30af\u30c1\u30e5\u30a2\u30ea\u30c6\u30a3\u8a55\u4fa1\u306e\u305f\u3081\u306e\u30d9\u30f3\u30c1\u30de\u30fc\u30af\u3092\u7d39\u4ecb\u3059\u308b\u3002 \u6211\u3005\u306f,\u5927\u898f\u6a21\u8a00\u8a9e\u30e2\u30c7\u30eb\u304b\u3089\u751f\u6210\u3055\u308c\u305f\u5fdc\u7b54\u3092\u53ce\u96c6\u3057,\u5fae\u7c92\u306a\u65b9\u6cd5\u3067\u4e8b\u5b9f\u30e9\u30d9\u30eb\u3092\u6ce8\u91c8\u4ed8\u3051\u3059\u308b\u3002 \u305d\u306e\u7d50\u679c,\u691c\u7d22\u306f\u4e8b\u5b9f\u6027\u8a55\u4fa1\u306b\u5f79\u7acb\u3064\u304c,\u73fe\u5728\u306eLCM\u306f\u4e8b\u5b9f\u306e\u8aa4\u308a\u3092\u5fe0\u5b9f\u306b\u691c\u51fa\u3059\u308b\u306b\u306f\u4e0d\u5341\u5206\u3067\u3042\u308b\u3053\u3068\u304c\u308f\u304b\u3063\u305f\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2310.00741v1\">\u8ad6\u6587<\/a>&nbsp;&nbsp;<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2310.00741v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>&nbsp; &nbsp;(Sun, 1 Oct 2023 17:37:31 GMT)<\/li>\n\n\n\n<li>world knowledge\u3001 science\/technology\u3001 writing\/recommendation\u3001 reasoning\u3001math\u306e\u30c9\u30e1\u30a4\u30f3\u304b\u3089\u306a\u308b\u30d9\u30f3\u30c1\u30de\u30fc\u30af\u3001\u30a2\u30ce\u30c6\u30fc\u30b7\u30e7\u30f3\u304c\u3081\u3063\u3061\u3083\u3057\u3093\u3069\u305d\u3046\u3002\u3002\u3002<\/li>\n\n\n\n<li>\u30ea\u30dd\u30b8\u30c8\u30ea\u306f<a href=\"https:\/\/github.com\/hkust-nlp\/felm\">GitHub &#8211; hkust-nlp\/felm: Github repository for &#8220;FELM: Benchmarking Factuality Evaluation of Large Language Models&#8221;<\/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":[223,517],"class_list":["post-3919","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-llm","tag-517"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/3919","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=3919"}],"version-history":[{"count":0,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/3919\/revisions"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=3919"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=3919"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=3919"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}