{"id":5553,"date":"2024-10-09T05:26:00","date_gmt":"2024-10-08T20:26:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=5553"},"modified":"2024-10-09T05:26:00","modified_gmt":"2024-10-08T20:26:00","slug":"easy2hard-bench-standardized-difficulty-labels-for-profiling-llm-performance-and-generalization","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=5553","title":{"rendered":"Easy2Hard-Bench: Standardized Difficulty Labels for Profiling LLM Performance and Generalization"},"content":{"rendered":"\n<ul class=\"wp-block-list\">\n<li><strong>Easy2Hard-Bench: Standardized Difficulty Labels for Profiling LLM Performance and Generalization&nbsp;<\/strong>[126.3]<br>\u3055\u307e\u3056\u307e\u306a\u30c9\u30e1\u30a4\u30f3\u306b\u307e\u305f\u304c\u308b6\u3064\u306e\u30d9\u30f3\u30c1\u30de\u30fc\u30af\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u306e\u30b3\u30ec\u30af\u30b7\u30e7\u30f3\u3067\u3042\u308bEasy2Hard-Bench\u3092\u7d39\u4ecb\u3057\u307e\u3059\u3002 \u3053\u308c\u3089\u306e\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u5185\u306e\u5404\u554f\u984c\u306f\u3001\u6570\u5024\u7684\u306a\u96e3\u6613\u5ea6\u30b9\u30b3\u30a2\u3067\u6ce8\u91c8\u4ed8\u3051\u3055\u308c\u308b\u3002 \u69d8\u3005\u306a\u96e3\u6613\u5ea6\u306b\u307e\u305f\u304c\u308b\u6027\u80fd\u3068\u4e00\u822c\u5316\u80fd\u529b\u3092\u7dcf\u5408\u7684\u306b\u5206\u6790\u3059\u308b\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2409.18433v1\">\u8ad6\u6587<\/a>&nbsp;&nbsp;<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2409.18433v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>&nbsp; &nbsp;(Fri, 27 Sep 2024 03:49:56 GMT)<\/li>\n\n\n\n<li>\u300cWhile generalization over tasks from easy to hard is crucial to profile language models (LLMs), the datasets with fine-grained difficulty annotations for each problem across a broad range of complexity are still blank.\u300d\u3068\u306e\u3053\u3068\u3067\u4f5c\u3089\u308c\u305f\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u3002\u9762\u767d\u3044\u50be\u5411\u304c\u51fa\u3066\u3044\u308b\u4e00\u65b9\u3067LLM\u306e\u30d9\u30f3\u30c1\u30de\u30fc\u30af\u3067\u4e3b\u8981\u306a\u5bfe\u8c61\u306b\u3055\u308c\u3066\u3044\u308b\u3068\u3053\u308d\u306f\u96e3\u6613\u5ea6\u3092\u5206\u3051\u308b\u306e\u306b\u3082\u82e6\u52b4\u3057\u305d\u3046\u306a\u5370\u8c61\u304c\u3042\u308b\u3002<\/li>\n\n\n\n<li>\u30ea\u30dd\u30b8\u30c8\u30ea\u306f<a href=\"https:\/\/huggingface.co\/datasets\/furonghuang-lab\/Easy2Hard-Bench\">furonghuang-lab\/Easy2Hard-Bench \u00b7 Datasets at Hugging Face<\/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":[121,517],"class_list":["post-5553","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-easy2hard","tag-517"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/5553","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=5553"}],"version-history":[{"count":0,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/5553\/revisions"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=5553"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=5553"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=5553"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}