{"id":3947,"date":"2023-10-31T05:31:00","date_gmt":"2023-10-30T20:31:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=3947"},"modified":"2023-10-31T05:31:00","modified_gmt":"2023-10-30T20:31:00","slug":"personalized-large-language-model-alignment","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=3947","title":{"rendered":"Personalized Large Language Model Alignment"},"content":{"rendered":"\n<ul class=\"wp-block-list\">\n<li><strong>Personalized Soups: Personalized Large Language Model Alignment via Post-hoc Parameter Merging&nbsp;<\/strong>[148.8]<br>\u30d1\u30fc\u30bd\u30ca\u30e9\u30a4\u30ba\u3055\u308c\u305f\u30d2\u30e5\u30fc\u30de\u30f3\u30d5\u30a3\u30fc\u30c9\u30d0\u30c3\u30af(RLPHF)\u554f\u984c\u304b\u3089\u306e\u5f37\u5316\u5b66\u7fd2\u306b\u3064\u3044\u3066\u691c\u8a0e\u3059\u308b\u3002 LLM\u306f\u3001\u591a\u76ee\u7684\u5f37\u5316\u5b66\u7fd2(MORL)\u554f\u984c\u3068\u3057\u3066\u30a2\u30e9\u30a4\u30e1\u30f3\u30c8\u3092\u30e2\u30c7\u30eb\u5316\u3059\u308b\u3053\u3068\u3067\u3001\u8907\u6570\u306e\u597d\u307f\u306b\u6574\u5217\u3059\u308b\u3002 \u6211\u3005\u306f\u3001\u597d\u307f\u3092\u8907\u6570\u306e\u6b21\u5143\u306b\u5206\u89e3\u3059\u308b\u3053\u3068\u3067\u3001\u30d1\u30fc\u30bd\u30ca\u30e9\u30a4\u30ba\u3055\u308c\u305f\u30a2\u30e9\u30a4\u30e1\u30f3\u30c8\u3092\u5b9f\u73fe\u3059\u308b\u3053\u3068\u304c\u3067\u304d\u308b\u3053\u3068\u3092\u793a\u3059\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2310.11564v1\">\u8ad6\u6587<\/a>&nbsp;&nbsp;<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2310.11564v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>&nbsp; &nbsp;(Tue, 17 Oct 2023 20:22:13 GMT)<\/li>\n\n\n\n<li>RLHF\u306b\u304a\u3044\u3066\u30d1\u30fc\u30bd\u30ca\u30e9\u30a4\u30ba\u3055\u308c\u305f\u65b9\u5411\u306b\u30a2\u30e9\u30a4\u30e1\u30f3\u30c8\u3059\u308bP-MORL: PROMPTED-MORL\u3001P-SOUP: PERSONALIZED SOUPS\u3092\u63d0\u6848\u3002\u4eba\u306b\u3088\u308b\u8a55\u4fa1\u3068GPT-4\u306b\u3088\u308b\u8a55\u4fa1\u304c\u5272\u308c\u3066\u3044\u308b\u306e\u3082\u8208\u5473\u6df1\u3044\u3068\u3053\u308d\u3002\u3002<\/li>\n\n\n\n<li>\u30ea\u30dd\u30b8\u30c8\u30ea\u306f<a href=\"https:\/\/github.com\/joeljang\/RLPHF\">GitHub &#8211; joeljang\/RLPHF: Personalized Soups: Personalized Large Language Model Alignment via Post-hoc Parameter Merging<\/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":[22,223],"class_list":["post-3947","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-alignment","tag-llm"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/3947","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=3947"}],"version-history":[{"count":0,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/3947\/revisions"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=3947"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=3947"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=3947"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}