{"id":3973,"date":"2023-10-26T05:39:00","date_gmt":"2023-10-25T20:39:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=3973"},"modified":"2023-10-26T05:39:00","modified_gmt":"2023-10-25T20:39:00","slug":"llm%e3%82%92%e5%90%ab%e3%82%80%e9%87%91%e8%9e%8d%e5%88%86%e9%87%8e%e3%81%aenlp%e8%a9%95%e4%be%a1","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=3973","title":{"rendered":"LLM\u3092\u542b\u3080\u91d1\u878d\u5206\u91ce\u306eNLP\u8a55\u4fa1"},"content":{"rendered":"\n<ul class=\"wp-block-list\">\n<li><strong>Is ChatGPT a Financial Expert? Evaluating Language Models on Financial Natural Language Processing&nbsp;<\/strong>[22.8]<br>FinLMEval\u306f\u91d1\u878d\u8a00\u8a9e\u30e2\u30c7\u30eb\u8a55\u4fa1\u306e\u305f\u3081\u306e\u30d5\u30ec\u30fc\u30e0\u30ef\u30fc\u30af\u3067\u3042\u308b\u3002 \u672c\u7814\u7a76\u3067\u306f,\u30a8\u30f3\u30b3\u30fc\u30c0\u306e\u307f\u306e\u8a00\u8a9e\u30e2\u30c7\u30eb\u3068\u30c7\u30b3\u30fc\u30c0\u306e\u307f\u306e\u8a00\u8a9e\u30e2\u30c7\u30eb\u306e\u6027\u80fd\u3092\u6bd4\u8f03\u3057\u305f\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2310.12664v1\">\u8ad6\u6587<\/a>&nbsp;&nbsp;<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2310.12664v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>&nbsp; &nbsp;(Thu, 19 Oct 2023 11:43:15 GMT)<\/li>\n\n\n\n<li>\u8907\u6570\u306e\u91d1\u878d\u5206\u91ce\u3067\u306e\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u3067BERT\u306a\u3069encoder\u7cfb\u30e2\u30c7\u30eb\uff0bfinetuning\u3001LLM\u3092\u6bd4\u8f03\u3001\u300cOur results show that fine-tuning expert encoder-only models generally perform better than the decoder-only LLMs on the financial NLP tasks, and adding in-context demonstrations barely improves the results.\u300d\u3068\u306e\u3053\u3068\u3002\u524d\u534a\u306f\u305d\u3046\u3060\u308d\u3046\u3068\u3044\u3046\u7d50\u679c\u3060\u304c\u3001\u5f8c\u534a\u306f\u3061\u3087\u3063\u3068\u4e0d\u601d\u8b70\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":[223,665],"class_list":["post-3973","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-llm","tag-665"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/3973","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=3973"}],"version-history":[{"count":0,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/3973\/revisions"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=3973"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=3973"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=3973"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}