{"id":3887,"date":"2023-10-03T06:12:00","date_gmt":"2023-10-02T21:12:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=3887"},"modified":"2023-10-03T06:12:00","modified_gmt":"2023-10-02T21:12:00","slug":"autocalibrate-%e4%ba%ba%e9%96%93%e3%81%ae%e5%a5%bd%e3%81%bf%e3%81%ab%e5%90%88%e3%82%8f%e3%81%9b%e3%81%9fllm%e5%88%a9%e7%94%a8%e3%81%ae%e8%a9%95%e4%be%a1%e5%99%a8","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=3887","title":{"rendered":"AUTOCALIBRATE \/ \u4eba\u9593\u306e\u597d\u307f\u306b\u5408\u308f\u305b\u305fLLM\u5229\u7528\u306e\u8a55\u4fa1\u5668"},"content":{"rendered":"\n<ul class=\"wp-block-list\">\n<li><strong>Calibrating LLM-Based Evaluator\u00a0<\/strong>[92.2]<br>\u30de\u30eb\u30c1\u30b9\u30c6\u30fc\u30b8\u3067\u52fe\u914d\u306e\u306a\u3044\u30a2\u30d7\u30ed\u30fc\u30c1\u3067\u3042\u308bAutoCalibrate\u3092\u63d0\u6848\u3057,LLM\u306b\u57fa\u3065\u304f\u8a55\u4fa1\u5668\u3092\u4eba\u9593\u306e\u597d\u307f\u306b\u5408\u308f\u305b\u3066\u8abf\u6574\u30fb\u8abf\u6574\u3059\u308b\u3002 \u4eba\u9593\u306e\u55dc\u597d\u3092\u660e\u793a\u7684\u306b\u30e2\u30c7\u30eb\u5316\u3059\u308b\u4ee3\u308f\u308a\u306b\u3001\u307e\u305a\u6697\u9ed9\u7684\u306b\u4eba\u9593\u306e\u30e9\u30d9\u30eb\u306b\u542b\u3081\u307e\u3059\u3002 \u8907\u6570\u306e\u30c6\u30ad\u30b9\u30c8\u54c1\u8cea\u8a55\u4fa1\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u306b\u95a2\u3059\u308b\u5b9f\u9a13\u306f\u3001\u6821\u6b63\u306b\u3088\u308b\u5c02\u9580\u5bb6\u8a55\u4fa1\u3068\u306e\u76f8\u95a2\u6027\u3092\u5927\u5e45\u306b\u6539\u5584\u3057\u305f\u3053\u3068\u3092\u793a\u3059\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2309.13308v1\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2309.13308v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Sat, 23 Sep 2023 08:46:11 GMT)<\/li>\n\n\n\n<li>LLM\u3092\u6d3b\u7528\u3057\u305f\u8a55\u4fa1\u5668\u3092\u4eba\u9593\u306e\u8a55\u4fa1\u306b\u5bc4\u305b\u308b\u624b\u6cd5\u3092\u63d0\u6848\u3002\u4eba\u304c\u8a55\u4fa1\u3057\u305f\u30c7\u30fc\u30bf\u3092\u3082\u3068\u306b\u8a55\u4fa1\u57fa\u6e96\u3092LLM\u306b\u66f8\u304b\u305b\u3066\u3001\u826f\u3044\u57fa\u6e96\u3092\u9078\u629e\uff06ICL\u3068\u3044\u3046\u30d7\u30ed\u30bb\u30b9\u3002<\/li>\n\n\n\n<li>LLM\u3092\u4eba\u3063\u307d\u304f\u4f7f\u3063\u3066\u3044\u308b\u70b9\u304c\u975e\u5e38\u306b\u8208\u5473\u6df1\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":[223,224,647],"class_list":["post-3887","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-llm","tag-llm-as-a-judge","tag-647"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/3887","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=3887"}],"version-history":[{"count":0,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/3887\/revisions"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=3887"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=3887"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=3887"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}