{"id":4832,"date":"2024-05-09T05:31:00","date_gmt":"2024-05-08T20:31:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=4832"},"modified":"2024-05-09T05:31:00","modified_gmt":"2024-05-08T20:31:00","slug":"causal-evaluation-of-language-models","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=4832","title":{"rendered":"Causal Evaluation of Language Models\u00a0"},"content":{"rendered":"\n<ul class=\"wp-block-list\">\n<li><strong>Causal Evaluation of Language Models\u00a0<\/strong>[33.3]<br>\u8a00\u8a9e\u30e2\u30c7\u30eb\u306e\u56e0\u679c\u7684\u63a8\u8ad6\u80fd\u529b\u3092\u8a55\u4fa1\u3059\u308b\u305f\u3081\u306e\u7dcf\u5408\u7684\u306a\u30d9\u30f3\u30c1\u30de\u30fc\u30af\u3068\u3057\u3066,CaLM(Causal Evaluation of Language Models)\u304c\u3042\u308b\u3002 CaLM\u306f4\u3064\u306e\u30e2\u30b8\u30e5\u30fc\u30eb\u304b\u3089\u306a\u308b\u5206\u985e\u6cd5\u3067\u3042\u308a\u3001\u56e0\u679c\u7684\u5bfe\u8c61(\u8a55\u4fa1\u5bfe\u8c61)\u3001\u9069\u5fdc(\u7d50\u679c\u306e\u53d6\u5f97\u65b9\u6cd5)\u3001\u30e1\u30fc\u30c8\u30eb\u6cd5(\u7d50\u679c\u306e\u6e2c\u5b9a\u65b9\u6cd5)\u3001\u30a8\u30e9\u30fc(\u60aa\u3044\u7d50\u679c\u306e\u5206\u6790\u65b9\u6cd5)\u3067\u3042\u308b\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2405.00622v1\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2405.00622v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Wed, 01 May 2024 16:43:21 GMT)<\/li>\n\n\n\n<li>LLM\u306e\u56e0\u679c\u7684\u306a\u63a8\u8ad6\u3092\u8a55\u4fa1\u3059\u308b\u305f\u3081\u306e\u30d9\u30f3\u30c1\u30de\u30fc\u30af\u3001Causal Evaluation of Language Models (CaLM)\u306e\u63d0\u6848\u3001GPT-4\u304cLeaderboard\u30c8\u30c3\u30d7\u3060\u304c\u3001\u6700\u65b0\u306e\u30e2\u30c7\u30eb\u3067\u306e\u691c\u8a3c\u7d50\u679c\u3092\u77e5\u308a\u305f\u3044\u3068\u3053\u308d<\/li>\n\n\n\n<li>\u30d7\u30ed\u30b8\u30a7\u30af\u30c8\u30b5\u30a4\u30c8\u306f<a href=\"https:\/\/opencausalab.github.io\/CaLM\/\">Causal Evaluation of Language Models (opencausalab.github.io)<\/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":[223,491,517],"class_list":["post-4832","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-llm","tag-491","tag-517"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/4832","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=4832"}],"version-history":[{"count":0,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/4832\/revisions"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=4832"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=4832"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=4832"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}