{"id":4179,"date":"2023-12-28T05:53:00","date_gmt":"2023-12-27T20:53:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=4179"},"modified":"2023-12-28T05:53:00","modified_gmt":"2023-12-27T20:53:00","slug":"promptbench","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=4179","title":{"rendered":"PromptBench"},"content":{"rendered":"\n<ul class=\"wp-block-list\">\n<li><strong>PromptBench: A Unified Library for Evaluation of Large Language Models\u00a0<\/strong>[33.8]<br>\u5927\u898f\u6a21\u8a00\u8a9e\u30e2\u30c7\u30eb(LLM)\u3092\u8a55\u4fa1\u3059\u308b\u7d71\u5408\u30e9\u30a4\u30d6\u30e9\u30ea\u3067\u3042\u308bPromptBench\u3092\u7d39\u4ecb\u3059\u308b\u3002 \u30d7\u30ed\u30f3\u30d7\u30c8\u69cb\u7bc9\u3001\u30d7\u30ed\u30f3\u30d7\u30c8\u30a8\u30f3\u30b8\u30cb\u30a2\u30ea\u30f3\u30b0\u3001\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u3068\u30e2\u30c7\u30eb\u306e\u30ed\u30fc\u30c7\u30a3\u30f3\u30b0\u3001\u6575\u306e\u30d7\u30ed\u30f3\u30d7\u30c8\u30a2\u30bf\u30c3\u30af\u3001\u52d5\u7684\u8a55\u4fa1\u30d7\u30ed\u30c8\u30b3\u30eb\u3001\u5206\u6790\u30c4\u30fc\u30eb\u306a\u3069\u3001\u7814\u7a76\u8005\u304c\u4f7f\u3044\u3084\u3059\u304f\u62e1\u5f35\u3057\u305f\u91cd\u8981\u306a\u30b3\u30f3\u30dd\u30fc\u30cd\u30f3\u30c8\u3067\u69cb\u6210\u3055\u308c\u3066\u3044\u308b\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2312.07910v1\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2312.07910v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Wed, 13 Dec 2023 05:58:34 GMT)<\/li>\n\n\n\n<li>LLM\uff08\u306b\u5bfe\u3059\u308b\u30d7\u30ed\u30f3\u30d7\u30c8\uff09\u306e\u8a55\u4fa1\u3092\u884c\u3046\u305f\u3081\u306e\u30d5\u30ec\u30fc\u30e0\u30ef\u30fc\u30af\u3002\u7c21\u5358\u306b\u4f7f\u3048\u305d\u3046\uff06\u4fbf\u5229\u305d\u3046<\/li>\n\n\n\n<li>\u30ea\u30dd\u30b8\u30c8\u30ea\u306f<a href=\"https:\/\/github.com\/microsoft\/promptbench\">GitHub &#8211; microsoft\/promptbench: A unified evaluation framework for large language models<\/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":[313,517],"class_list":["post-4179","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-prompt","tag-517"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/4179","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=4179"}],"version-history":[{"count":0,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/4179\/revisions"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=4179"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=4179"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=4179"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}