{"id":4013,"date":"2023-11-06T05:22:00","date_gmt":"2023-11-05T20:22:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=4013"},"modified":"2023-11-06T05:22:00","modified_gmt":"2023-11-05T20:22:00","slug":"lema-learning-from-mistakes","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=4013","title":{"rendered":"LEMA: LEarning from MistAkes"},"content":{"rendered":"\n<ul class=\"wp-block-list\">\n<li><strong>Learning From Mistakes Makes LLM Better Reasoner&nbsp;<\/strong>[112.8]<br>\u5927\u898f\u6a21\u8a00\u8a9e\u30e2\u30c7\u30eb(LLM)\u306f\u3001\u6700\u8fd1\u6570\u5b66\u306e\u554f\u984c\u3092\u89e3\u304f\u969b\u3001\u9855\u8457\u306a\u63a8\u8ad6\u80fd\u529b\u3092\u793a\u3057\u305f\u3002 \u3053\u306e\u7814\u7a76\u306f\u3001\u4eba\u9593\u306e\u5b66\u7fd2\u30d7\u30ed\u30bb\u30b9\u306b\u4f3c\u305f\u3001\u30df\u30b9\u30c6\u30a4\u30af\u304b\u3089\u306e\u5b66\u7fd2(LeMa)\u3092\u63d0\u6848\u3059\u308b\u3002 <br><a href=\"http:\/\/arxiv.org\/abs\/2310.20689v1\">\u8ad6\u6587<\/a>&nbsp;&nbsp;<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2310.20689v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>&nbsp; &nbsp;(Tue, 31 Oct 2023 17:52:22 GMT)<\/li>\n\n\n\n<li>\u00a0GPT-4\u3092\u7528\u3044\u3066\u300c (1) identify the mistake step, (2) explain the reason for the mistake, (3) correct the mistake and generate the final answer\u300d\u3068\u3044\u3046\u624b\u9806\u3067\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u3092\u4f5c\u6210\u3001fine tuning\u306b\u3088\u308aCoT\u30c7\u30fc\u30bf\u306b\u6bd4\u3079\u3066\u6027\u80fd\u304c\u5927\u5e45\u306b\u5411\u4e0a\u3057\u305f\u3068\u306e\u5831\u544a\u3002\u8aa4\u308a\u306e\u65b9\u304c\u5b66\u7fd2\u52b9\u7387\u304c\u826f\u3044\uff08\u65b0\u305f\u306a\u60c5\u5831\u304c\u591a\u3044\uff09\u306e\u306f\u305d\u3046\u306a\u3093\u3060\u308d\u3046\u3068\u601d\u3046\u3002<\/li>\n\n\n\n<li>\u30ea\u30dd\u30b8\u30c8\u30ea\u306f<a href=\"https:\/\/github.com\/microsoft\/CodeT\">GitHub &#8211; microsoft\/CodeT<\/a>\u3000\uff1f<\/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],"class_list":["post-4013","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-llm"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/4013","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=4013"}],"version-history":[{"count":0,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/4013\/revisions"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=4013"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=4013"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=4013"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}