{"id":6680,"date":"2025-05-16T03:32:00","date_gmt":"2025-05-15T18:32:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=6680"},"modified":"2025-05-10T16:52:36","modified_gmt":"2025-05-10T07:52:36","slug":"toward-generalizable-evaluation-in-the-llm-era-a-survey-beyond-benchmarks","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=6680","title":{"rendered":"Toward Generalizable Evaluation in the LLM Era: A Survey Beyond Benchmarks"},"content":{"rendered":"\n<ul class=\"wp-block-list\">\n<li><strong>Toward Generalizable Evaluation in the LLM Era: A Survey Beyond Benchmarks\u00a0<\/strong>[229.7]<br>\u3053\u306e\u8abf\u67fb\u306f\u3001\u5927\u898f\u6a21\u8a00\u8a9e\u30e2\u30c7\u30eb\u306e\u53f0\u982d\u304c\u8a55\u4fa1\u306b\u5f79\u7acb\u3063\u3066\u3044\u308b\u4e2d\u6838\u7684\u306a\u8ab2\u984c\u3092\u8abf\u67fb\u3059\u308b\u3002 i) \u30bf\u30b9\u30af\u56fa\u6709\u306e\u3082\u306e\u304b\u3089\u80fd\u529b\u306b\u57fa\u3065\u304f\u8a55\u4fa1\u3078\u3068\u3001\u77e5\u8b58\u3001\u63a8\u8ad6\u3001\u6307\u793a\u306b\u5f93\u3046\u3053\u3068\u3001\u30de\u30eb\u30c1\u30e2\u30fc\u30c0\u30eb\u7406\u89e3\u3001\u5b89\u5168\u6027\u3068\u3044\u3063\u305f\u30b3\u30a2\u80fd\u529b\u306b\u95a2\u3059\u308b\u30d9\u30f3\u30c1\u30de\u30fc\u30af\u3092\u518d\u7de8\u6210\u3059\u308b\u3002 \u3053\u306e\u554f\u984c\u3068\u3001\u4e0a\u8a18\u306e2\u3064\u306e\u30c8\u30e9\u30f3\u30b8\u30b7\u30e7\u30f3\u306e\u4e2d\u6838\u7684\u306a\u8ab2\u984c\u3092\u3001\u30e1\u30bd\u30c3\u30c9\u3001\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u3001\u8a55\u4fa1\u5668\u3001\u30e1\u30c8\u30ea\u30af\u30b9\u306e\u89b3\u70b9\u304b\u3089\u691c\u8a0e\u3059\u308b\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2504.18838v1\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2504.18838v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Sat, 26 Apr 2025 07:48:52 GMT)<\/li>\n\n\n\n<li>\u30d9\u30f3\u30c1\u30de\u30fc\u30af\u306b\u95a2\u3059\u308b\u30b5\u30fc\u30d9\u30a4\u3002\u300cFig6 Illustration of capability-based benchmark taxonomy involving: knowledge, reasoning, instruction following, multimodal, and safety.\u300d\u304c\u8996\u899a\u7684\u306b\u3068\u3066\u3082\u5206\u304b\u308a\u3084\u3059\u3044\u3002<\/li>\n\n\n\n<li>\u30ea\u30dd\u30b8\u30c8\u30ea\u306f<a href=\"https:\/\/github.com\/ALEX-nlp\/Benchmark-of-core-capabilities\">GitHub &#8211; ALEX-nlp\/Benchmark-of-core-capabilities<\/a>\u3001<\/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":[387,517],"class_list":["post-6680","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-survey","tag-517"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/6680","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=6680"}],"version-history":[{"count":1,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/6680\/revisions"}],"predecessor-version":[{"id":6716,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/6680\/revisions\/6716"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=6680"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=6680"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=6680"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}