{"id":3458,"date":"2023-06-19T06:17:00","date_gmt":"2023-06-18T21:17:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=3458"},"modified":"2023-06-19T06:17:00","modified_gmt":"2023-06-18T21:17:00","slug":"cmmlu-chinese-massive-multitask-language-understanding","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=3458","title":{"rendered":"CMMLU: Chinese Massive Multitask Language Understanding"},"content":{"rendered":"\n<ul class=\"wp-block-list\">\n<li><strong>CMMLU: Measuring massive multitask language understanding in Chinese\u00a0<\/strong>[121.8]<br>\u672c\u7a3f\u3067\u306f, \u81ea\u7136\u79d1\u5b66, \u793e\u4f1a\u79d1\u5b66, \u5de5\u5b66, \u4eba\u6587\u79d1\u5b66\u306a\u3069, \u3055\u307e\u3056\u307e\u306a\u5206\u91ce\u3092\u30ab\u30d0\u30fc\u3059\u308b\u7dcf\u5408\u7684\u306a\u4e2d\u56fd\u306e\u30d9\u30f3\u30c1\u30de\u30fc\u30af\u3092\u7d39\u4ecb\u3059\u308b\u3002 CMMLU\u306f\u3001\u4e2d\u56fd\u8a9e\u306e\u6587\u8108\u306b\u304a\u3051\u308b\u5927\u304d\u306a\u8a00\u8a9e\u30e2\u30c7\u30eb\u306e\u77e5\u8b58\u3068\u63a8\u8ad6\u80fd\u529b\u306e\u8a55\u4fa1\u306b\u304a\u3051\u308b\u30ae\u30e3\u30c3\u30d7\u3092\u57cb\u3081\u308b\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2306.09212v1\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2306.09212v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Thu, 15 Jun 2023 15:49:51 GMT)<\/li>\n\n\n\n<li>\u4e2d\u56fd\u8a9e\u306e\u7dcf\u5408\u30d9\u30f3\u30c1\u30de\u30fc\u30af\u3001\u4e2d\u56fd\u8a9e\u56fa\u6709\u306e\u56de\u7b54\u306a\u3069\u304c\u542b\u307e\u308c\u308b\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u3067\u3042\u308b\u3068\u306e\u3053\u3068\u3002\u6b63\u7b54\u7387\u306fChatGPT\u3067\u308255.51%\u3068\u96e3\u3057\u3044\u30bf\u30b9\u30af\uff08\u30e9\u30f3\u30c0\u30e0\u56de\u7b54\u3060\u306825%\uff09\u3001OSS\u306a\u30e2\u30c7\u30eb\u306e\u30d9\u30b9\u30c8\u306fFalcon-40B\u306e41.45%\u3001LLaMA 65B\u306f39.80%\u3068ChatGPT\u304b\u3089\u306e\u6027\u80fd\u5dee\u306f\u5927\u304d\u3044\u3002ChatGLM-6B\u306e37.48%\u3001BLOOMZ-7B\u306e37.04%\u3092\u898b\u308b\u306b\u4e2d\u56fd\u8a9e\u306b\u5bfe\u5fdc\u3055\u305b\u306b\u884c\u304f\u65b9\u5411\u6027\u306f\u6709\u52b9\u305d\u3046\u3067\u306f\u3042\u308b\u3002<\/li>\n\n\n\n<li>\u30ea\u30dd\u30b8\u30c8\u30ea\u306f<a href=\"https:\/\/github.com\/haonan-li\/CMMLU\">GitHub &#8211; haonan-li\/CMMLU<\/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-3458","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\/3458","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=3458"}],"version-history":[{"count":0,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/3458\/revisions"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=3458"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=3458"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=3458"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}