{"id":3906,"date":"2023-10-13T05:50:00","date_gmt":"2023-10-12T20:50:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=3906"},"modified":"2023-10-13T05:50:00","modified_gmt":"2023-10-12T20:50:00","slug":"mpsc-multi-perspective-self-consistency","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=3906","title":{"rendered":"MPSC: Multi-Perspective Self-Consistency"},"content":{"rendered":"\n<ul class=\"wp-block-list\">\n<li><strong>Enhancing Large Language Models in Coding Through Multi-Perspective Self-Consistency\u00a0<\/strong>[137.3]<br>\u5927\u898f\u6a21\u8a00\u8a9e\u30e2\u30c7\u30eb(LLM)\u306e\u305f\u3081\u306eMPSC(Multi-Perspective Self-Consistency)\u30d5\u30ec\u30fc\u30e0\u30ef\u30fc\u30af\u3092\u63d0\u6848\u3059\u308b\u3002 MPSC\u306f\u3001\u8907\u6570\u306e\u8996\u70b9\u304b\u3089\u306e\u51fa\u529b\u9593\u3067\u306e\u4e00\u8cab\u6027\u3068\u3001\u5358\u4e00\u306e\u8996\u70b9\u5185\u3067\u306e\u4e00\u8cab\u6027\u306e\u4e21\u65b9\u3092\u53d6\u308a\u5165\u308c\u3066\u3044\u308b\u3002 \u6211\u3005\u306e\u30d5\u30ec\u30fc\u30e0\u30ef\u30fc\u30af\u306f\u3001\u69d8\u3005\u306a\u4eba\u6c17\u306e\u3042\u308b\u30d9\u30f3\u30c1\u30de\u30fc\u30af\u306e\u30d1\u30d5\u30a9\u30fc\u30de\u30f3\u30b9\u3092\u5927\u5e45\u306b\u5411\u4e0a\u3055\u305b\u307e\u3059\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2309.17272v1\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2309.17272v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Fri, 29 Sep 2023 14:23:26 GMT)<\/li>\n\n\n\n<li>LLM\u306e\u8907\u6570\u306e\u51fa\u529b\u3092\u7528\u3044\u3001\u00a0inter- and intraconsistency\u00a0\u3092\u8003\u616e\u3057\u3066\u6700\u9069\u306a\u51fa\u529b\u3092\u9078\u629e\u3002\u901a\u5e38\u306eSelf consistency\u306a\u6226\u7565\u3092\u4e0a\u56de\u308b\u6027\u80fd\u3068\u306e\u3053\u3068\u3002<\/li>\n\n\n\n<li>\u300cOur MPSC framework significantly boosts the performance on various popular benchmarks, including HumanEval (+17.60%), HumanEval Plus (+17.61%), MBPP (+6.50%) and CodeContests (+11.82%) in Pass@1, when compared to original outputs generated from ChatGPT, and even surpassing GPT-4.\u300d\u306f\u3059\u3054\u3044\u3002<\/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-3906","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\/3906","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=3906"}],"version-history":[{"count":0,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/3906\/revisions"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=3906"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=3906"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=3906"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}