{"id":3591,"date":"2023-07-27T05:20:00","date_gmt":"2023-07-26T20:20:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=3591"},"modified":"2023-07-27T05:20:00","modified_gmt":"2023-07-26T20:20:00","slug":"flask-fine-grained-language-model-evaluation-based-on-alignment-skill-sets","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=3591","title":{"rendered":"FLASK (Fine-grained Language Model Evaluation based on Alignment SKill Sets)"},"content":{"rendered":"\n<ul class=\"wp-block-list\">\n<li><strong>FLASK: Fine-grained Language Model Evaluation based on Alignment Skill Sets\u00a0<\/strong>[39.8]<br>FLASK\u306f\u3001\u7c97\u5ea6\u30b9\u30b3\u30a2\u30ea\u30f3\u30b0\u3092\u30a4\u30f3\u30b9\u30bf\u30f3\u30b9\u5358\u4f4d\u306e\u30b9\u30ad\u30eb\u30bb\u30c3\u30c8\u30ec\u30d9\u30eb\u306b\u5206\u89e3\u3059\u308b\u3001\u304d\u3081\u7d30\u304b\u3044\u8a55\u4fa1\u30d7\u30ed\u30c8\u30b3\u30eb\u3067\u3042\u308b\u3002 \u5177\u4f53\u7684\u306b\u306f\u3001LLM\u304c\u30aa\u30fc\u30d7\u30f3\u30a8\u30f3\u30c9\u30e6\u30fc\u30b6\u30fc\u6307\u793a\u306b\u5f93\u3046\u305f\u3081\u306b\u5fc5\u8981\u306a12\u306e\u304d\u3081\u7d30\u304b\u3044\u30b9\u30ad\u30eb\u3092\u5b9a\u7fa9\u3059\u308b\u3002 FLASK\u306f\u3001\u30b9\u30ad\u30eb\u3001\u30c9\u30e1\u30a4\u30f3\u3001\u96e3\u6613\u5ea6\u306b\u5fdc\u3058\u3066\u3001\u30e2\u30c7\u30eb\u306e\u30d1\u30d5\u30a9\u30fc\u30de\u30f3\u30b9\u3092\u5305\u62ec\u7684\u306b\u5206\u6790\u3057\u305f\u7dcf\u5408\u7684\u306a\u30d3\u30e5\u30fc\u3092\u63d0\u4f9b\u3059\u308b\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2307.10928v1\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2307.10928v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Thu, 20 Jul 2023 14:56:35 GMT)<\/li>\n\n\n\n<li>\u30e6\u30fc\u30b6\u306e\u6307\u793a\u306b\u5f93\u3046\u305f\u3081\u306e\u30b9\u30ad\u30eb\u3092\u8a55\u4fa1\u3059\u308b\u305f\u3081\u306e\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u30fb\u30d9\u30f3\u30c1\u30de\u30fc\u30af\u306e\u63d0\u6848\u3002\u8a55\u4fa1\u8ef8\u306f\u00a0Logical Thinking (Logical Robustness, Logical Correctness, Logical Efficiency)\u3001Background Knowledge (Factuality, Commonsense Understanding)\u3001Problem Handling (Comprehension, Insightfulness, Completeness, Metacognition)\u3001User Alignment (Readability, Conciseness, Harmlessness)<\/li>\n\n\n\n<li>\u7d50\u679c\u3068\u3057\u3066\u306f\u5546\u7528\u30e2\u30c7\u30eb\u306e\u5f37\u529b\u3055\u3068\u3001\u305d\u306e\u4e2d\u3067\u3082GPT-4\u306e\u5f37\u3055\u304c\u76ee\u7acb\u3064\u3002<\/li>\n\n\n\n<li>\u30d7\u30ed\u30b8\u30a7\u30af\u30c8\u30b5\u30a4\u30c8\u306f<a href=\"https:\/\/github.com\/kaistAI\/FLASK\">GitHub &#8211; kaistAI\/FLASK: Official codebase for &#8220;FLASK: Fine-grained Language Model Evaluation based on Alignment Skill Sets&#8221;<\/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":[223,491],"class_list":["post-3591","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-llm","tag-491"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/3591","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=3591"}],"version-history":[{"count":0,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/3591\/revisions"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=3591"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=3591"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=3591"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}