
  <rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
    <channel>
      <title>HARRY CHANG</title>
      <link>https://harrychang.cc/blog</link>
      <description>Harry Chang 的數位園藝。利用 AI 整理與記錄個人的興趣與知識庫，如果你也有相同興趣，歡迎隨意參觀。</description>
      <language>zh-TW</language>
      <managingEditor>ksharry1025@gmail.com (HARRY CHANG)</managingEditor>
      <webMaster>ksharry1025@gmail.com (HARRY CHANG)</webMaster>
      <lastBuildDate>Tue, 29 Sep 2026 00:00:00 GMT</lastBuildDate>
      <atom:link href="https://harrychang.cc/tags/rag/feed.xml" rel="self" type="application/rss+xml"/>
      
  <item>
    <guid>https://harrychang.cc/blog/ai-099-paper-conversational-question-reformulation</guid>
    <title>Paper 099 ｜對話式問答的基礎：利用 Seq2Seq 與預訓練語言模型進行問題改寫</title>
    <link>https://harrychang.cc/blog/ai-099-paper-conversational-question-reformulation</link>
    <description>閱讀 2020 論文 Conversational Question Reformulation via Sequence-to-Sequence Architectures and Pretrained Language Models。探討在對話式搜尋中，如何利用模型將包含省略或代名詞的模糊問題，改寫為完整且獨立的查詢語句，這也是現代 Agent 處理連續對話的必備前置作業。</description>
    <pubDate>Tue, 29 Sep 2026 00:00:00 GMT</pubDate>
    <author>ksharry1025@gmail.com (HARRY CHANG)</author>
    <category>AI相關</category><category>Paper-檢索</category><category>RAG</category>
  </item>

  <item>
    <guid>https://harrychang.cc/blog/ai-100-paper-multi-stage-conversational-passage-retrieval</guid>
    <title>Paper 100 ｜多階段對話式段落檢索：從歷史脈絡精準抓取對話意圖</title>
    <link>https://harrychang.cc/blog/ai-100-paper-multi-stage-conversational-passage-retrieval</link>
    <description>閱讀 2020 論文 Multi-Stage Conversational Passage Retrieval。本篇進一步將對話式檢索推向多階段架構，探討如何在長對話中，過濾掉閒聊與無關雜訊，精準檢索出能回答使用者當下需求的段落。</description>
    <pubDate>Tue, 29 Sep 2026 00:00:00 GMT</pubDate>
    <author>ksharry1025@gmail.com (HARRY CHANG)</author>
    <category>AI相關</category><category>Paper-檢索</category><category>RAG</category>
  </item>

    </channel>
  </rss>
