{"id":4944,"date":"2024-06-03T06:01:00","date_gmt":"2024-06-02T21:01:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=4944"},"modified":"2024-06-03T06:01:00","modified_gmt":"2024-06-02T21:01:00","slug":"auto-arena-of-llms-automating-llm-evaluations-with-agent-peer-battles-and-committee-discussions","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=4944","title":{"rendered":"Auto Arena of LLMs: Automating LLM Evaluations with Agent Peer-battles and Committee Discussions"},"content":{"rendered":"\n<ul class=\"wp-block-list\">\n<li><strong>Auto Arena of LLMs: Automating LLM Evaluations with Agent Peer-battles and Committee Discussions\u00a0<\/strong>[77.8]<br>LLM \u30a8\u30fc\u30b8\u30a7\u30f3\u30c8\u306b\u3088\u308b\u8a55\u4fa1\u30d7\u30ed\u30bb\u30b9\u5168\u4f53\u3092\u81ea\u52d5\u5316\u3057\u305f LLM \u306e\u81ea\u52d5\u30a2\u30ea\u30fc\u30ca\u3092\u63d0\u6848\u3059\u308b\u3002 \u6700\u65b0\u306eLLM17\u5b9f\u9a13\u306b\u304a\u3044\u3066,\u30aa\u30fc\u30c8\u30a2\u30ea\u30fc\u30ca\u306f\u4eba\u9593\u306e\u55dc\u597d\u3068\u6700\u3082\u9ad8\u3044\u76f8\u95a2\u95a2\u4fc2\u3092\u793a\u3057\u305f\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2405.20267v1\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2405.20267v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Thu, 30 May 2024 17:19:19 GMT)<\/li>\n\n\n\n<li>LLM\u306e\u8a55\u4fa1\u624b\u6cd5\u306e\u63d0\u6848\u3001\u300cBy using LLM agents to generate questions, employing LLM candidates in peer battles, and evaluating responses using LLM committee discussions, Auto-Arena produces less-contaminated, robust, and trustworthy evaluation results.\u300d\u3068\u3044\u3046\u30a8\u30fc\u30b8\u30a7\u30f3\u30c8\u7684\u624b\u6cd5\u3002\u81ea\u52d5\u8a55\u4fa1\u304c\u3067\u304d\u308b\u3068\u3044\u3046\u3053\u3068\u306f\u81ea\u52d5\u6539\u5584\u3082\u3067\u304d\u305d\u3046\u306a\u6c17\u304c\u3059\u308b\u304c\u3001\u5408\u8b70\u5236\u3067\u826f\u3044\u30c7\u30fc\u30bf\u3092\u4f5c\u308afine tuning\u3092\u3057\u3066\u3044\u304f\u3068\u3069\u306e\u304f\u3089\u3044\u307e\u3067\u6027\u80fd\u304c\u4e0a\u304c\u308b\u3093\u3060\u308d\u3046\u304b\u3002<\/li>\n\n\n\n<li>\u30d7\u30ed\u30b8\u30a7\u30af\u30c8\u30b5\u30a4\u30c8\u30fb\u30ea\u30fc\u30c0\u30fc\u30dc\u30fc\u30c9\u306f<a href=\"https:\/\/auto-arena.github.io\/\">Embedded Streamlit App (auto-arena.github.io)<\/a>\u3001\u82f1\u8a9e\u3068\u4e2d\u56fd\u8a9e\u3067\u30e9\u30f3\u30ad\u30f3\u30b0\u304c\u304b\u306a\u308a\u7570\u306a\u308b\u306e\u304c\u9762\u767d\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":[42,223,647],"class_list":["post-4944","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-autonomous-agent","tag-llm","tag-647"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/4944","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=4944"}],"version-history":[{"count":0,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/4944\/revisions"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=4944"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=4944"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=4944"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}