{"id":5809,"date":"2024-11-29T06:37:00","date_gmt":"2024-11-28T21:37:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=5809"},"modified":"2024-11-29T06:37:00","modified_gmt":"2024-11-28T21:37:00","slug":"search-verify-and-feedback-towards-next-generation-post-training-paradigm-of-foundation-models-via-verifier-engineering","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=5809","title":{"rendered":"Search, Verify and Feedback: Towards Next Generation Post-training Paradigm of Foundation Models via Verifier Engineering\u00a0"},"content":{"rendered":"\n<ul class=\"wp-block-list\">\n<li><strong>Search, Verify and Feedback: Towards Next Generation Post-training Paradigm of Foundation Models via Verifier Engineering\u00a0<\/strong>[51.3]<br>\u691c\u8a3c\u5de5\u5b66\u306f\u3001\u57fa\u790e\u30e2\u30c7\u30eb\u306e\u6642\u4ee3\u306e\u305f\u3081\u306b\u7279\u5225\u306b\u8a2d\u8a08\u3055\u308c\u305f\u65b0\u3057\u3044\u30dd\u30b9\u30c8\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0\u30d1\u30e9\u30c0\u30a4\u30e0\u3067\u3042\u308b\u3002 \u691c\u8a3c\u5de5\u5b66\u306e\u30d7\u30ed\u30bb\u30b9\u306f,\u691c\u7d22,\u691c\u8a3c,\u30d5\u30a3\u30fc\u30c9\u30d0\u30c3\u30af\u306e3\u6bb5\u968e\u306b\u5206\u985e\u3059\u308b\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2411.11504v1\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2411.11504v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Mon, 18 Nov 2024 12:04:52 GMT)<\/li>\n\n\n\n<li>\u300cThe essence of verifier engineering lies in extending the construction of supervision signals beyond traditional manual feature extraction and data annotation. Instead, it utilizes a suite of effective automated verifiers to perform verification tasks and provide meaningful feedback to foundation models.\u300d\u3068\u3044\u3046verifier engineering \u306e\u63d0\u6848\u3002\u91cd\u8981\u6027\u304c\u5897\u3057\u3066\u3044\u308b\u5206\u91ce\u306a\u306e\u306f\u9593\u9055\u3044\u306a\u3044\u3068\u601d\u3046\u3001<\/li>\n\n\n\n<li>\u30ea\u30dd\u30b8\u30c8\u30ea\u306f<a href=\"https:\/\/github.com\/icip-cas\/Verifier-Engineering\">GitHub &#8211; icip-cas\/Verifier-Engineering: Search, Verify and Feedback: Towards Next Generation Post-training Paradigm of Foundation Models via Verifier Engineering<\/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":[224,430],"class_list":["post-5809","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-llm-as-a-judge","tag-verifier-engineering"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/5809","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=5809"}],"version-history":[{"count":0,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/5809\/revisions"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=5809"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=5809"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=5809"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}