{"id":4457,"date":"2024-02-22T04:55:00","date_gmt":"2024-02-21T19:55:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=4457"},"modified":"2024-02-22T04:55:00","modified_gmt":"2024-02-21T19:55:00","slug":"the-generative-ai-paradox-on-evaluation","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=4457","title":{"rendered":"The Generative AI Paradox on Evaluation\u00a0"},"content":{"rendered":"\n<ul class=\"wp-block-list\">\n<li><strong>The Generative AI Paradox on Evaluation: What It Can Solve, It May Not Evaluate\u00a0<\/strong>[17.8]<br>\u672c\u7a3f\u3067\u306f,\u30b8\u30a7\u30cd\u30ec\u30fc\u30b7\u30e7\u30f3\u30bf\u30b9\u30af\u306b\u304a\u3051\u308bLarge Language Models (LLMs) \u304c\u540c\u7b49\u306b\u8a55\u4fa1\u3067\u304d\u308b\u3068\u3044\u3046\u4eee\u5b9a\u3092\u8003\u5bdf\u3059\u308b\u3002 \u8cea\u554f\u5fdc\u7b54(QA)\u306b\u304a\u3051\u308b3\u3064\u306eLLM\u30681\u3064\u306e\u30aa\u30fc\u30d7\u30f3\u30bd\u30fc\u30b9LM\u306e\u6027\u80fd\u8a55\u4fa1\u3068,TriviaQA\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u3092\u7528\u3044\u305f\u8a55\u4fa1\u8ab2\u984c\u306b\u3064\u3044\u3066\u8ff0\u3079\u308b\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2402.06204v1\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2402.06204v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Fri, 9 Feb 2024 06:16:08 GMT)<\/li>\n\n\n\n<li>\u554f\u984c\u89e3\u6c7a\u3068\u8a55\u4fa1\u80fd\u529b\u306f\u5225\u306a\u306e\u3067\u306f\uff1f\u3068\u3044\u3046\u554f\u3044\u3078\u306e\u691c\u8a3c\u3002\u300cResults indicate a significant disparity, with LLMs exhibiting lower performance in evaluation tasks compared to generation tasks\u300d\u3068\u306e\u3053\u3068<\/li>\n\n\n\n<li>TriviaQA\u00a0\u3067\u306e\u691c\u8a3c\u3060\u304c\u3001\u304a\u305d\u3089\u304f\u30bf\u30b9\u30af\u3084\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u306b\u3088\u3063\u3066\u7570\u306a\u308b\u3093\u3060\u308d\u3046\u3068\u306f\u601d\u3046\u3002\u8a55\u4fa1\u7528\u306b\u751f\u6210AI\u3092\u4f7f\u3046\u3053\u3068\u306f\u591a\u3044\u304c\u305d\u308d\u305d\u308dGPT-4\u304c\u4ed6\u3092\u5727\u5012\u3068\u3044\u3046\u308f\u3051\u3067\u3082\u306a\u304f\u306a\u3063\u3066\u3044\u308b\u306e\u3067\u8208\u5473\u6df1\u3044\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":[223,647],"class_list":["post-4457","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-llm","tag-647"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/4457","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=4457"}],"version-history":[{"count":0,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/4457\/revisions"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=4457"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=4457"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=4457"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}