{"id":3640,"date":"2023-08-04T05:10:00","date_gmt":"2023-08-03T20:10:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=3640"},"modified":"2023-08-04T05:10:00","modified_gmt":"2023-08-03T20:10:00","slug":"l-eval","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=3640","title":{"rendered":"L-Eval"},"content":{"rendered":"\n<ul class=\"wp-block-list\">\n<li><strong>L-Eval: Instituting Standardized Evaluation for Long Context Language Models\u00a0<\/strong>[45.8]<br>\u9577\u3044\u6587\u8108\u8a00\u8a9e\u30e2\u30c7\u30eb\u306f\u30011\u30bf\u30fc\u30f3\u306e\u9577\u3044\u5165\u529b(\u4f8b\u3048\u3070\u3001\u8ad6\u6587\u306e\u8981\u7d04)\u3092\u51e6\u7406\u3057\u3001\u3088\u308a\u5e83\u7bc4\u306a\u6b74\u53f2\u3068\u4f1a\u8a71\u3059\u308b\u3053\u3068\u304c\u3067\u304d\u308b\u3002 L-Eval\u306f411\u306e\u9577\u3044\u30c9\u30ad\u30e5\u30e1\u30f3\u30c8\u30682000\u4ee5\u4e0a\u306e\u30af\u30a8\u30ea\u5fdc\u7b54\u30da\u30a2\u3092\u624b\u52d5\u3067\u30a2\u30ce\u30c6\u30fc\u30c8\u3057\u3001\u8457\u8005\u306b\u3088\u3063\u3066\u30c1\u30a7\u30c3\u30af\u3055\u308c\u308b\u3002 \u79c1\u305f\u3061\u306e\u8abf\u67fb\u7d50\u679c\u306f\u3001\u30aa\u30fc\u30d7\u30f3\u30bd\u30fc\u30b9\u30e2\u30c7\u30eb\u306f\u4e00\u822c\u7684\u306b\u5546\u7528\u30e2\u30c7\u30eb\u3088\u308a\u3082\u9045\u308c\u3066\u3044\u308b\u3082\u306e\u306e\u3001\u305d\u308c\u3067\u3082\u7d20\u6674\u3089\u3057\u3044\u30d1\u30d5\u30a9\u30fc\u30de\u30f3\u30b9\u3092\u793a\u3057\u3066\u3044\u308b\u3053\u3068\u3092\u793a\u5506\u3057\u3066\u3044\u307e\u3059\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2307.11088v1\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2307.11088v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Thu, 20 Jul 2023 17:59:41 GMT)<\/li>\n\n\n\n<li>\u9577\u6587\u3092\u6271\u3046\u30d9\u30f3\u30c1\u30de\u30fc\u30af\u3067\u30bf\u30b9\u30af\u306f\u69d8\u3005\uff08\u9078\u629e\u5f0f\u306e\u8cea\u554f\u56de\u7b54\u3001Question Answering\u3001\u8981\u7d04\u306a\u3069\uff09\u3001\u300cGPT3.5-16k and Claude-100k are more advanced compared to the open-source models\u300d\u3068\u306e\u3053\u3068\u3067\u3053\u306e\u5dee\u304c\u7e2e\u307e\u3063\u3066\u3044\u304f\u304b\u8208\u5473\u6d25\u3005<\/li>\n\n\n\n<li>\u30ea\u30dd\u30b8\u30c8\u30ea\u306f<a href=\"https:\/\/github.com\/OpenLMLab\/LEval\">GitHub &#8211; OpenLMLab\/LEval: Data and code for L-Eval, a comprehensive long context language models evaluation benchmark<\/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":[491,517,667],"class_list":["post-3640","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-491","tag-517","tag-667"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/3640","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=3640"}],"version-history":[{"count":0,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/3640\/revisions"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=3640"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=3640"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=3640"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}