{"id":6340,"date":"2025-03-04T06:06:00","date_gmt":"2025-03-03T21:06:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=6340"},"modified":"2025-03-04T06:06:00","modified_gmt":"2025-03-03T21:06:00","slug":"self-rewarding-correction-for-mathematical-reasoning","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=6340","title":{"rendered":"Self-rewarding correction for mathematical reasoning\u00a0"},"content":{"rendered":"\n<ul class=\"wp-block-list\">\n<li><strong>Self-rewarding correction for mathematical reasoning\u00a0<\/strong>[19.5]<br>\u6211\u3005\u306f,\u5927\u898f\u6a21\u8a00\u8a9e\u30e2\u30c7\u30eb(LLM)\u306e\u81ea\u5df1\u56de\u5e30\u7684\u63a8\u8ad6\u306b\u3064\u3044\u3066\u7814\u7a76\u3059\u308b\u3002 LLM\u306f\u3001\u30b9\u30c6\u30c3\u30d7\u30d0\u30a4\u30b9\u30c6\u30c3\u30d7\u306e\u63a8\u8ad6\u3092\u540c\u6642\u306b\u751f\u6210\u3057\u3001\u5916\u90e8\u304b\u3089\u306e\u30d5\u30a3\u30fc\u30c9\u30d0\u30c3\u30af\u3092\u4f34\u308f\u306a\u3044\u63a8\u8ad6\u6642\u9593\u306b\u304a\u3051\u308b\u51fa\u529b\u306e\u6b63\u3057\u3055\u3092\u8a55\u4fa1\u3059\u308b\u3002 \u672c\u7a3f\u3067\u306f,\u81ea\u5df1\u751f\u6210\u30c7\u30fc\u30bf\u306e\u307f\u3092\u7528\u3044\u3066\u81ea\u5df1\u56de\u5e30\u63a8\u8ad6\u30e2\u30c7\u30eb\u3092\u69cb\u7bc9\u3059\u308b\u305f\u3081\u306e2\u6bb5\u968e\u306e\u30a2\u30eb\u30b4\u30ea\u30ba\u30e0\u30d5\u30ec\u30fc\u30e0\u30ef\u30fc\u30af\u3092\u63d0\u6848\u3059\u308b\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2502.19613v1\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2502.19613v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Wed, 26 Feb 2025 23:01:16 GMT)<\/li>\n\n\n\n<li>\u300cself-rewarding reasoning framework for LLMs, which integrates the generator and reward model into a single LLM, enabling autonomous reasoning, evaluation, and correction.\u300d\u3001\u300cself-correction in mathematical reasoning and propose a two-stage framework that relies only on self-generated data.\u300d\u306e\u63d0\u6848\u3002<\/li>\n\n\n\n<li>\u30ea\u30dd\u30b8\u30c8\u30ea\u306f<a href=\"https:\/\/github.com\/RLHFlow\/Self-rewarding-reasoning-LLM\">GitHub &#8211; RLHFlow\/Self-rewarding-reasoning-LLM: Recipes to train the self-rewarding reasoning LLMs.<\/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":[356],"class_list":["post-6340","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-self-x"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/6340","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=6340"}],"version-history":[{"count":0,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/6340\/revisions"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=6340"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=6340"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=6340"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}