{"id":5754,"date":"2024-11-11T07:24:00","date_gmt":"2024-11-10T22:24:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=5754"},"modified":"2024-11-11T07:24:00","modified_gmt":"2024-11-10T22:24:00","slug":"htmlrag-html-is-better-than-plain-text-for-modeling-retrieved-knowledge-in-rag-systems","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=5754","title":{"rendered":"HtmlRAG: HTML is Better Than Plain Text for Modeling Retrieved Knowledge in RAG Systems"},"content":{"rendered":"\n<ul class=\"wp-block-list\">\n<li><strong>HtmlRAG: HTML is Better Than Plain Text for Modeling Retrieved Knowledge in RAG Systems\u00a0<\/strong>[62.4]<br>Retrieval-Augmented Generation (RAG) \u306f\u77e5\u8b58\u80fd\u529b\u306e\u5411\u4e0a\u3092\u76ee\u7684\u3068\u3057\u3066\u3044\u308b\u3002 HTML RAG\u306f\u3001\u691c\u7d22\u3055\u308c\u305f\u77e5\u8b58\u306e\u30d5\u30a9\u30fc\u30de\u30c3\u30c8\u3068\u3057\u3066\u3001\u5e73\u6613\u306a\u30c6\u30ad\u30b9\u30c8\u306e\u4ee3\u308f\u308a\u306bHTML\u3092\u4f7f\u7528\u3059\u308b\u3002 \u6211\u3005\u306f,\u60c5\u5831\u306e\u640d\u5931\u3092\u6700\u5c0f\u9650\u306b\u6291\u3048\u3064\u3064,HTML\u306e\u77ed\u7e2e\u5316\u3092\u56f3\u308b\u305f\u3081,HTML\u306e\u30af\u30ea\u30fc\u30cb\u30f3\u30b0,\u5727\u7e2e,\u30d7\u30eb\u30fc\u30cb\u30f3\u30b0\u6226\u7565\u3092\u63d0\u6848\u3059\u308b\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2411.02959v1\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2411.02959v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Tue, 05 Nov 2024 09:58:36 GMT)<\/li>\n\n\n\n<li>RAG\u3067\u4f7f\u7528\u3059\u308b\u77e5\u8b58\u306e\u30d5\u30a9\u30fc\u30de\u30c3\u30c8\u3068\u3057\u3066HTML\u3092\u4f7f\u7528\u3059\u308b\u3068\u3044\u3046\u63d0\u6848\u3001\u30d9\u30f3\u30c1\u30de\u30fc\u30af\u3067\u3082\u512a\u308c\u305f\u7d50\u679c\u3068\u306e\u3053\u3068\u3002\u30d9\u30fc\u30b9LLM\uff08Llama 3.1 8B\u30fb70B\uff09\u00d7\u63d0\u6848\u624b\u6cd5\u30fbPlainText\u30fbMarkdown\u306e\u7d50\u679c\u304c\u8208\u5473\u6df1\u3044\u3002\uff08HTML\u304c\u30d9\u30b9\u30c8\u306a\u306e\u304b\u8aad\u307f\u53d6\u308b\u306e\u304c\u96e3\u3057\u3044\u3088\u3046\u306a\u6c17\u304c\u3057\u306a\u304f\u3082\u306a\u3044\uff09<\/li>\n\n\n\n<li>\u30ea\u30dd\u30b8\u30c8\u30ea\u306f<a href=\"https:\/\/github.com\/plageon\/HtmlRAG\">GitHub &#8211; plageon\/HtmlRAG: HtmlRAG: HTML is Better Than Plain Text for Modeling Retrieval Results in RAG Systems<\/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":[324],"class_list":["post-5754","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-rag"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/5754","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=5754"}],"version-history":[{"count":0,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/5754\/revisions"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=5754"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=5754"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=5754"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}