{"id":5371,"date":"2024-09-10T05:39:00","date_gmt":"2024-09-09T20:39:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=5371"},"modified":"2024-09-10T05:39:00","modified_gmt":"2024-09-09T20:39:00","slug":"a-survey-on-evaluating-large-language-models-in-code-generation-tasks","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=5371","title":{"rendered":"A Survey on Evaluating Large Language Models in Code Generation Tasks"},"content":{"rendered":"\n<ul class=\"wp-block-list\">\n<li><strong>A Survey on Evaluating Large Language Models in Code Generation Tasks\u00a0<\/strong>[30.3]<br>\u672c\u7a3f\u3067\u306f,\u30b3\u30fc\u30c9\u751f\u6210\u30bf\u30b9\u30af\u306b\u304a\u3051\u308bLarge Language Models (LLMs) \u306e\u6027\u80fd\u8a55\u4fa1\u306b\u4f7f\u7528\u3055\u308c\u308b\u73fe\u5728\u306e\u624b\u6cd5\u3068\u6307\u6a19\u306b\u3064\u3044\u3066\u6982\u8aac\u3059\u308b\u3002 \u81ea\u52d5\u30bd\u30d5\u30c8\u30a6\u30a7\u30a2\u958b\u767a\u306e\u9700\u8981\u304c\u6025\u901f\u306b\u5897\u52a0\u3057\u3001LLM\u306f\u30b3\u30fc\u30c9\u751f\u6210\u306e\u5206\u91ce\u3067\u5927\u304d\u306a\u53ef\u80fd\u6027\u3092\u793a\u3057\u3066\u304d\u305f\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2408.16498v1\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2408.16498v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Thu, 29 Aug 2024 12:56:06 GMT)<\/li>\n\n\n\n<li>\u76db\u308a\u4e0a\u304c\u3063\u3066\u304d\u3066\u3044\u308b\u30b3\u30fc\u30c9\u751f\u6210\u30bf\u30b9\u30af\u306b\u3064\u3044\u3066\u3001\u305d\u306e\u8a55\u4fa1\u624b\u6cd5\u3092\u307e\u3068\u3081\u305f\u30b5\u30fc\u30d9\u30a4<\/li>\n\n\n\n<li>\u6a5f\u68b0\u7ffb\u8a33\u3067\u3082\u4e00\u822c\u7684\u306a\u300cEvaluation Based on Similarity\u300d\u306e\u307b\u304b\u3001\u300cExecution-Based Evaluation\u300d\u3001\u300c\u00a0Feedback-Based Evaluation\u300d\u306a\u3069\u304c\u3042\u3063\u3066\u8208\u5473\u6df1\u3044\u3002<\/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":[387,468,647],"class_list":["post-5371","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-survey","tag-468","tag-647"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/5371","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=5371"}],"version-history":[{"count":0,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/5371\/revisions"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=5371"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=5371"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=5371"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}