{"id":4844,"date":"2024-05-06T03:46:00","date_gmt":"2024-05-05T18:46:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=4844"},"modified":"2024-05-06T03:46:00","modified_gmt":"2024-05-05T18:46:00","slug":"score-self-correction-ability-in-reasoning-tasks","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=4844","title":{"rendered":"SCORE: Self-COrrection ability in REasoning tasks"},"content":{"rendered":"\n<ul class=\"wp-block-list\">\n<li><strong>Small Language Models Need Strong Verifiers to Self-Correct Reasoning\u00a0<\/strong>[69.9]<br>\u5927\u898f\u6a21\u8a00\u8a9e\u30e2\u30c7\u30eb(LLM)\u306e\u63a8\u8ad6\u6027\u80fd\u3092\u9ad8\u3081\u308b\u305f\u3081\u306e\u6709\u671b\u306a\u30bd\u30ea\u30e5\u30fc\u30b7\u30e7\u30f3\u3068\u3057\u3066\u81ea\u5df1\u88dc\u6b63\u304c\u767b\u5834\u3057\u305f\u3002 \u672c\u7814\u7a76\u306f,\u3088\u308a\u5c0f\u3055\u3044 (= 13B) \u8a00\u8a9e\u30e2\u30c7\u30eb (LM) \u304c,\u3088\u308a\u5f37\u3044 LM \u304b\u3089\u6700\u5c0f\u9650\u306e\u5165\u529b\u3067\u63a8\u8ad6\u30bf\u30b9\u30af\u3092\u81ea\u5df1\u88dc\u6b63\u3067\u304d\u308b\u304b\u3069\u3046\u304b\u3092\u8003\u5bdf\u3059\u308b\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2404.17140v1\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2404.17140v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Fri, 26 Apr 2024 03:41:28 GMT)<\/li>\n\n\n\n<li>\u81ea\u5df1\u88dc\u6b63\u3092\u5f37\u5316\u3059\u308b\u305f\u3081\u306efine tuning\u30d7\u30ed\u30bb\u30b9\u306e\u63d0\u6848\u3002\u5b66\u7fd2\u7528\u30c7\u30fc\u30bf\u3092\u30e2\u30c7\u30eb\u306b\u4f5c\u3089\u305b\u308b\u30a2\u30d7\u30ed\u30fc\u30c1\u3067\u81ea\u5206\u81ea\u8eab\u3092\u5f37\u5316\u3057\u3066\u3044\u308b\u611f\u304c\u3042\u308b\u3002<\/li>\n\n\n\n<li>\u30ea\u30dd\u30b8\u30c8\u30ea\u306f<a href=\"https:\/\/github.com\/yunx-z\/SCORE\">https:\/\/github.com\/yunx-z\/SCORE<\/a>\u3068\u306e\u3053\u3068\u3060\u304c\u3001\u73fe\u5728\u306fNotFound<\/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":[223,390],"class_list":["post-4844","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-llm","tag-synthetic-data"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/4844","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=4844"}],"version-history":[{"count":0,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/4844\/revisions"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=4844"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=4844"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=4844"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}