{"id":5484,"date":"2024-09-26T04:27:00","date_gmt":"2024-09-25T19:27:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=5484"},"modified":"2024-09-26T04:27:00","modified_gmt":"2024-09-25T19:27:00","slug":"a-controlled-study-on-long-context-extension-and-generalization-in-llms","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=5484","title":{"rendered":"A Controlled Study on Long Context Extension and Generalization in LLMs"},"content":{"rendered":"\n<ul class=\"wp-block-list\">\n<li><strong>A Controlled Study on Long Context Extension and Generalization in LLMs\u00a0<\/strong>[85.5]<br>\u5e83\u7fa9\u306e\u30c6\u30ad\u30b9\u30c8\u7406\u89e3\u3068\u30c6\u30ad\u30b9\u30c8\u5185\u5b66\u7fd2\u306f\u3001\u5b8c\u5168\u306a\u6587\u66f8\u30b3\u30f3\u30c6\u30ad\u30b9\u30c8\u3092\u5229\u7528\u3059\u308b\u8a00\u8a9e\u30e2\u30c7\u30eb\u3092\u5fc5\u8981\u3068\u3059\u308b\u3002 \u9577\u671f\u30b3\u30f3\u30c6\u30ad\u30b9\u30c8\u30e2\u30c7\u30eb\u3092\u76f4\u63a5\u8a13\u7df4\u3059\u308b\u969b\u306e\u5b9f\u88c5\u4e0a\u306e\u8ab2\u984c\u306e\u305f\u3081\u3001\u9577\u671f\u30b3\u30f3\u30c6\u30ad\u30b9\u30c8\u3092\u6271\u3046\u305f\u3081\u306b\u30e2\u30c7\u30eb\u3092\u62e1\u5f35\u3059\u308b\u591a\u304f\u306e\u65b9\u6cd5\u304c\u63d0\u6848\u3055\u308c\u3066\u3044\u308b\u3002 \u6211\u3005\u306f,\u4e00\u8cab\u3057\u305f\u30d9\u30fc\u30b9\u30e2\u30c7\u30eb\u3068\u62e1\u5f35\u30c7\u30fc\u30bf\u3092\u5229\u7528\u3057\u3066,\u6a19\u6e96\u5316\u3055\u308c\u305f\u8a55\u4fa1\u306b\u3088\u308b\u62e1\u5f35\u30e1\u30bd\u30c3\u30c9\u306e\u5236\u5fa1\u30d7\u30ed\u30c8\u30b3\u30eb\u3092\u5b9f\u88c5\u3057\u305f\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2409.12181v1\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2409.12181v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Wed, 18 Sep 2024 17:53:17 GMT)<\/li>\n\n\n\n<li>\u9577\u6587\u306e\u53d6\u308a\u6271\u3044\u306b\u95a2\u3059\u308b\u624b\u6cd5\u306e\u8a55\u4fa1\u3001\u300cOur study underscores the role of perplexity as a crucial, performance indicator at length and highlights the trade-offs inherent in different attention mechanisms.\u300d<\/li>\n\n\n\n<li>\u30ea\u30dd\u30b8\u30c8\u30ea\u306f<a href=\"https:\/\/github.com\/Leooyii\/LCEG\">GitHub &#8211; Leooyii\/LCEG: Long Context Extension and Generalization in LLMs<\/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":[223,667],"class_list":["post-5484","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-llm","tag-667"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/5484","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=5484"}],"version-history":[{"count":0,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/5484\/revisions"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=5484"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=5484"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=5484"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}