{"id":6433,"date":"2025-03-17T05:13:00","date_gmt":"2025-03-16T20:13:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=6433"},"modified":"2025-03-17T05:13:00","modified_gmt":"2025-03-16T20:13:00","slug":"a-survey-on-post-training-of-large-language-models","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=6433","title":{"rendered":"A Survey on Post-training of Large Language Models\u00a0"},"content":{"rendered":"\n<ul class=\"wp-block-list\">\n<li><strong>A Survey on Post-training of Large Language Models\u00a0<\/strong>[185.5]<br>\u5927\u898f\u6a21\u8a00\u8a9e\u30e2\u30c7\u30eb(LLM)\u306f\u3001\u81ea\u7136\u8a00\u8a9e\u51e6\u7406\u3092\u6839\u672c\u7684\u306b\u5909\u9769\u3057\u3001\u4f1a\u8a71\u30b7\u30b9\u30c6\u30e0\u304b\u3089\u79d1\u5b66\u7684\u63a2\u7d22\u307e\u3067\u3001\u3055\u307e\u3056\u307e\u306a\u9818\u57df\u3067\u6b20\u304b\u305b\u306a\u3044\u3082\u306e\u306b\u3057\u3066\u3044\u308b\u3002 \u3053\u308c\u3089\u306e\u8ab2\u984c\u306f\u3001\u5236\u9650\u3055\u308c\u305f\u63a8\u8ad6\u80fd\u529b\u3001\u502b\u7406\u7684\u4e0d\u78ba\u5b9f\u6027\u3001\u6700\u9069\u306a\u30c9\u30e1\u30a4\u30f3\u56fa\u6709\u306e\u30d1\u30d5\u30a9\u30fc\u30de\u30f3\u30b9\u3068\u3044\u3063\u305f\u6b20\u70b9\u306b\u5bfe\u51e6\u3059\u308b\u305f\u3081\u306b\u3001\u5148\u9032\u7684\u306a\u8a13\u7df4\u5f8c\u8a00\u8a9e\u30e2\u30c7\u30eb(PoLM)\u3092\u5fc5\u8981\u3068\u3059\u308b\u3002 \u672c\u7a3f\u3067\u306f,5\u3064\u306e\u30b3\u30a2\u30d1\u30e9\u30c0\u30a4\u30e0\u306b\u307e\u305f\u304c\u308bPoLM\u306e\u9032\u5316\u3092\u4f53\u7cfb\u7684\u306b\u8ffd\u8de1\u3059\u308b,\u6700\u521d\u306e\u5305\u62ec\u7684\u8abf\u67fb\u306b\u3064\u3044\u3066\u8ff0\u3079\u308b\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2503.06072v1\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2503.06072v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Sat, 08 Mar 2025 05:41:42 GMT)<\/li>\n\n\n\n<li><a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2502.21321v1\">Fugu-MT \u8ad6\u6587\u7ffb\u8a33(\u6982\u8981): LLM Post-Training: A Deep Dive into Reasoning Large Language Models<\/a>\u3068\u306f\u5225\u30c1\u30fc\u30e0\u306b\u3088\u308bPost Traning\u306e\u30b5\u30fc\u30d9\u30a4<\/li>\n\n\n\n<li>\u300cThis paper offers the first exhaustive survey of Post-training Language Models (PoLMs), systematically tracing their trajectory from ChatGPT\u2019s alignment origins in 2018 to DeepSeek-R1\u2019s reasoning milestone in 2025, and affirming their transformative influence on reasoning precision, domain adaptability, and ethical integrity.\u300d\u3068\u3042\u308b\u901a\u308a\u3001\u6700\u65b0\u306e\u60c5\u5831\u3092\u542b\u3080\u30b5\u30fc\u30d9\u30a4\u306757\u30da\u30fc\u30b8\u3068\u3068\u3066\u3082\u5305\u62ec\u7684\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":[307,387],"class_list":["post-6433","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-post-training","tag-survey"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/6433","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=6433"}],"version-history":[{"count":0,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/6433\/revisions"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=6433"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=6433"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=6433"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}