{"id":4250,"date":"2024-01-09T05:27:00","date_gmt":"2024-01-08T20:27:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=4250"},"modified":"2024-01-09T05:27:00","modified_gmt":"2024-01-08T20:27:00","slug":"logicasker","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=4250","title":{"rendered":"LogicAsker"},"content":{"rendered":"\n<ul class=\"wp-block-list\">\n<li><strong>A &amp; B == B &amp; A: Triggering Logical Reasoning Failures in Large Language Models\u00a0<\/strong>[65.9]<br>LogicAsker\u306fLLM\u306e\u8ad6\u7406\u7684\u63a8\u8ad6\u80fd\u529b\u3092\u7dcf\u5408\u7684\u306b\u8a55\u4fa1\u3057\u6539\u5584\u3059\u308b\u81ea\u52d5\u624b\u6cd5\u3067\u3042\u308b\u3002 LogicAsker \u306f GPT-3, ChatGPT, GPT-4, Bard, Vicuna, Guanaco \u306e6\u7a2e\u985e\u306e LLM \u306b\u5bfe\u3057\u3066\u8a55\u4fa1\u3092\u884c\u3063\u305f\u3002 \u305d\u306e\u7d50\u679c\u3001LogicAsker\u306e\u30c6\u30b9\u30c8\u30b1\u30fc\u30b9\u306f\u3001\u7570\u306a\u308bLLM\u3067\u8ad6\u7406\u7684\u63a8\u8ad6\u5931\u6557\u309225%\u304b\u308994%\u306e\u78ba\u7387\u3067\u767a\u898b\u3067\u304d\u308b\u3053\u3068\u304c\u308f\u304b\u3063\u305f\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2401.00757v1\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2401.00757v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Mon, 1 Jan 2024 13:53:53 GMT)<\/li>\n\n\n\n<li>LLM\u306e\u8ad6\u7406\u7684\u63a8\u8ad6\uff08\u547d\u984c\u8ad6\u7406\u30fb\u8ff0\u8a9e\u8ad6\u7406\uff09\u80fd\u529b\u3092\u6e2c\u308b\u30d9\u30f3\u30c1\u30de\u30fc\u30af\u306e\u63d0\u6848\u3001ICL\u306b\u3088\u308b\u6539\u5584\u3082\u8a55\u4fa1\u3057\u3066\u3044\u308b\u3002\u30c7\u30fc\u30bf\u7b49\u306f\u516c\u958b\u4e88\u5b9a\u3068\u306e\u3053\u3068\u3060\u304c\u3001\u73fe\u6642\u70b9\u3067\u30ea\u30dd\u30b8\u30c8\u30ea\u306f\u898b\u3064\u3051\u3089\u308c\u306a\u304b\u3063\u305f\u3002<\/li>\n\n\n\n<li>GPT-4\u3067\u3082\u7d50\u69cb\u9593\u9055\u3046\u306a\u3001\u3068\u3044\u3046\u5370\u8c61<\/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],"class_list":["post-4250","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-llm"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/4250","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=4250"}],"version-history":[{"count":0,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/4250\/revisions"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=4250"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=4250"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=4250"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}