{"id":5955,"date":"2024-12-24T04:05:00","date_gmt":"2024-12-23T19:05:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=5955"},"modified":"2024-12-24T04:05:00","modified_gmt":"2024-12-23T19:05:00","slug":"a-survey-on-llm-inference-time-self-improvement","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=5955","title":{"rendered":"A Survey on LLM Inference-Time Self-Improvement"},"content":{"rendered":"\n<ul class=\"wp-block-list\">\n<li><strong>A Survey on LLM Inference-Time Self-Improvement\u00a0<\/strong>[15.0]<br>\u8fd1\u5e74,\u30c6\u30b9\u30c8\u6642\u306e\u8a08\u7b97\u91cf\u306e\u5897\u52a0\u306b\u3088\u308b\u63a8\u8ad6\u5411\u4e0a\u6280\u8853\u304c\u6ce8\u76ee\u3055\u308c\u3066\u3044\u308b\u3002 \u672c\u7a3f\u3067\u306f,\u6700\u8fd1\u306e\u7814\u7a76\u3092\u5305\u62ec\u7684\u306b\u30ec\u30d3\u30e5\u30fc\u3057,\u8a73\u7d30\u306a\u5206\u985e\u5b66\u306b\u8ca2\u732e\u3057,\u8ab2\u984c\u3068\u9650\u754c\u306b\u3064\u3044\u3066\u8b70\u8ad6\u3059\u308b\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2412.14352v1\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2412.14352v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Wed, 18 Dec 2024 21:37:07 GMT)<\/li>\n\n\n\n<li>\u6700\u8fd1\u8981\u6ce8\u76ee\uff08\uff1f\uff09\u306eInference time self improvement\u306e\u30b5\u30fc\u30d9\u30a4\u3002\u300cWe classify these methods into three categories: Independent Self-Improvement, which operates independently; Context-Aware Self-Improvement, which leverages external support (i.e. context and datastore retrieval); and Model-Aided Self-Improvement, which relies on external models for collaboration.\u300d\u3068\u3044\u3046\u8ef8\u3067\u6574\u7406\u3002<\/li>\n\n\n\n<li>\u30ea\u30dd\u30b8\u30c8\u30ea\u306f<a href=\"https:\/\/github.com\/dongxiangjue\/Awesome-LLM-Self-Improvement\">GitHub &#8211; dongxiangjue\/Awesome-LLM-Self-Improvement: A curated list of awesome LLM Inference-Time Self-Improvement (ITSI, pronounced &#8220;itsy&#8221;) papers from our recent survey: A Survey on Large Language Model Inference-Time Self-Improvement.<\/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":[387,398],"class_list":["post-5955","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-survey","tag-test-time-adaptation"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/5955","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=5955"}],"version-history":[{"count":0,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/5955\/revisions"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=5955"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=5955"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=5955"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}