{"id":6335,"date":"2025-03-13T05:52:00","date_gmt":"2025-03-12T20:52:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=6335"},"modified":"2025-03-13T05:52:00","modified_gmt":"2025-03-12T20:52:00","slug":"big-bench-extra-hard","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=6335","title":{"rendered":"BIG-Bench Extra Hard\u00a0"},"content":{"rendered":"\n<ul class=\"wp-block-list\">\n<li><strong>BIG-Bench Extra Hard\u00a0<\/strong>[98.4]<br>\u5927\u898f\u6a21\u8a00\u8a9e\u30e2\u30c7\u30eb(LLM)\u306f\u3001\u307e\u3059\u307e\u3059\u65e5\u5e38\u7684\u306a\u30a2\u30d7\u30ea\u30b1\u30fc\u30b7\u30e7\u30f3\u306b\u30c7\u30d7\u30ed\u30a4\u3055\u308c\u3001\u5805\u7262\u306a\u4e00\u822c\u7684\u306a\u63a8\u8ad6\u6a5f\u80fd\u3092\u5fc5\u8981\u3068\u3057\u3066\u3044\u308b\u3002 BIG-Bench\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u306f\u3001LLM\u306e\u4e00\u822c\u7684\u306a\u63a8\u8ad6\u80fd\u529b\u3092\u8a55\u4fa1\u3059\u308b\u305f\u3081\u306e\u91cd\u8981\u306a\u30d9\u30f3\u30c1\u30de\u30fc\u30af\u3068\u3057\u3066\u6a5f\u80fd\u3057\u3066\u3044\u308b\u3002 \u6700\u5148\u7aef\u306e\u30e2\u30c7\u30eb\u306f\u3001BIG-Bench\u306e\u591a\u304f\u306e\u30bf\u30b9\u30af\u306b\u304a\u3044\u3066\u307b\u307c\u5b8c\u74a7\u306a\u30b9\u30b3\u30a2\u3092\u5f97\u308b\u305f\u3081\u3001\u305d\u306e\u5b9f\u7528\u6027\u306f\u4f4e\u4e0b\u3059\u308b\u3002 BIG-Bench Extra Hard (BBEH) \u306f, LLM\u63a8\u8ad6\u8a55\u4fa1\u306e\u30d0\u30a6\u30f3\u30c0\u30ea\u3092\u63a8\u3057\u9032\u3081\u308b\u305f\u3081\u306e\u65b0\u3057\u3044\u30d9\u30f3\u30c1\u30de\u30fc\u30af\u3067\u3042\u308b\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2502.19187v1\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2502.19187v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Wed, 26 Feb 2025 14:50:50 GMT)<\/li>\n\n\n\n<li>BIG-Bench\u306e\u5f37\u5316\u7248\u3001\u300cSolving the tasks in BBEH requires even further reasoning skills than the problems in BBH. These skills include, but are not limited to, many-hop reasoning, learning on the fly, finding errors in reasoning traces, processing long-context inputs and finding (multi-)needles in a haystack, going against strong prior, dealing with long-range dependencies, dealing with distractors and inducing patterns from examples.\u300d\u3068\u63a8\u8ad6\u306b\u95a2\u3059\u308b\u80fd\u529b\u304c\u5fc5\u8981\u306b\u306a\u308b\u3088\u3046\u3002LRM\u3001o3-mini(high)\u306f\u307e\u305a\u307e\u305a\u306e\u30b9\u30b3\u30a2\u3067\u3042\u308b\u4e00\u65b9\u3067\u4e00\u90e8\u30bf\u30b9\u30af\u3092\u82e6\u624b\u3068\u3057\u3066\u3044\u308bDeepseek R1\u306e\u30b9\u30b3\u30a2\u304c\u4f4e\u3044\u306e\u304c\u8208\u5473\u6df1\u3044\u3002<\/li>\n\n\n\n<li>\u30ea\u30dd\u30b8\u30c8\u30ea\u306f<a href=\"https:\/\/github.com\/google-deepmind\/bbeh\">GitHub &#8211; google-deepmind\/bbeh<\/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":[223,517],"class_list":["post-6335","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-llm","tag-517"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/6335","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=6335"}],"version-history":[{"count":0,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/6335\/revisions"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=6335"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=6335"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=6335"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}