{"id":3828,"date":"2023-09-18T05:37:00","date_gmt":"2023-09-17T20:37:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=3828"},"modified":"2023-09-18T05:37:00","modified_gmt":"2023-09-17T20:37:00","slug":"ambiguity-aware-in-context-learning-with-large-language-models","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=3828","title":{"rendered":"Ambiguity-Aware In-Context Learning with Large Language Models"},"content":{"rendered":"\n<ul class=\"wp-block-list\">\n<li><strong>Ambiguity-Aware In-Context Learning with Large Language Models\u00a0<\/strong>[27.2]<br>\u30a4\u30f3\u30b3\u30f3\u30c6\u30ad\u30b9\u30c8\u5b66\u7fd2(ICL)\u3001\u3059\u306a\u308f\u3061\u3001LLM\u306e\u30bf\u30b9\u30af\u56fa\u6709\u306e\u30c7\u30e2\u306f\u3001\u30bf\u30b9\u30af\u56fa\u6709\u306e\u5fae\u8abf\u6574\u3092\u5fc5\u8981\u3068\u305b\u305a\u3001\u30c0\u30a6\u30f3\u30b9\u30c8\u30ea\u30fc\u30e0\u306e\u30b2\u30a4\u30f3\u306b\u3064\u306a\u304c\u3063\u305f\u3002 \u305d\u3053\u3067\u672c\u7814\u7a76\u3067\u306f,ICL\u306e\u512a\u308c\u305f\u5b9f\u6f14\u65b9\u6cd5\u306b\u3064\u3044\u3066\u691c\u8a0e\u3059\u308b\u3002 \u610f\u5473\u7684\u306b\u985e\u4f3c\u3057\u305fICL\u306e\u30c7\u30e2\u30f3\u30b9\u30c8\u30ec\u30fc\u30b7\u30e7\u30f3\u3092\u9078\u629e\u3059\u308b\u3060\u3051\u3067\u306a\u304f\u3001\u56fa\u6709\u306e\u30e9\u30d9\u30eb\u306e\u3042\u3044\u307e\u3044\u3055\u3092\u89e3\u6c7a\u3059\u308b\u306e\u306b\u5f79\u7acb\u3064\u3082\u306e\u3092\u9078\u629e\u3059\u308b\u3053\u3068\u306f\u6709\u76ca\u3067\u3042\u308b\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2309.07900v1\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2309.07900v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Thu, 14 Sep 2023 17:48:34 GMT)<\/li>\n\n\n\n<li>\u901a\u5e38\u3001\u610f\u5473\u7684\u306b\u8fd1\u3044\u3082\u306e\u3092\u5165\u308c\u308bIn-Context Learning\u3092\u6539\u5584\u3059\u308b\u5831\u544a\u3002\u300cInterestingly, we find that including demonstrations that the LLM previously mis-classified and also fall on the test example\u2019s decision boundary, brings the most performance gain.\u300d\u3068\u306e\u3053\u3068\u3002<\/li>\n\n\n\n<li>Input\u30c7\u30fc\u30bf\u3068\u306e\u985e\u4f3c\u6027\u3060\u3051\u3067\u306a\u304fLLM\u306e\u77e5\u8b58\u306e\u8003\u616e\u304c\u3055\u308c\u308b\u5206\u9ad8\u6027\u80fd\u306b\u306a\u308b\u3068\u3044\u3046\u306e\u306f\u300c\u78ba\u304b\u306b\u300d\u3068\u601d\u3046\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":[200],"class_list":["post-3828","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-in-context-learning"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/3828","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=3828"}],"version-history":[{"count":0,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/3828\/revisions"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=3828"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=3828"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=3828"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}