2026-06-22
【學術亮點-頂級會議論文】Smart Book Seeker:面向中介資料稀疏館藏之代理增強檢索系統
Font Size
Small
Middle
Large
【學術亮點-頂級會議論文】Smart Book Seeker:面向中介資料稀疏館藏之代理增強檢索系統
AI core Technology: Advanced Research and Resource Integration Platform or AI Technology【Department of Computer Science and Engineering / Yao-Chung Fan / Professor】
核心技術:AI核心技術之進階研究與資源整合平台資訊工程學系范耀中教授】
上架日期:2025/5/28
AI core Technology: Advanced Research and Resource Integration Platform or AI Technology【Department of Computer Science and Engineering / Yao-Chung Fan / Professor】
核心技術:AI核心技術之進階研究與資源整合平台資訊工程學系范耀中教授】
| 論文篇名 | 英文:Smart Book Seeker: Agent-Augmented Retrieval System for Metadata-Sparse Libraries 中文:Smart Book Seeker:面向中介資料稀疏館藏之代理增強檢索系統 |
| 期刊名稱 | WWW Companion '26: Companion Proceedings of the ACM Web Conference 2026 (指標清單會議) |
| 發表年份, 卷數, 起迄頁數 | In Companion Proceedings of the ACM Web Conference 2026 (WWW Companion '26) , pp.738–744, Dubai United Arab Emirates from June 29 – July 7, 2026. |
| 作者 | Hao-Quan Liu; Yao-Chung Fan(范耀中)∗ |
| DOI | 10.1145/3774905.3795723 |
| 中文摘要 | 許多圖書館僅以書名編目,缺乏主題標目或摘要等豐富的中介資料。此種中介資料稀疏引發一連串檢索挑戰:使用者在不知道確切書名時難以建構有效查詢、詞彙不匹配導致相關書籍被漏檢,且使用者常缺乏領域專業以判斷檢索結果是否真正符合需求。為解決這些限制,我們提出 Smart Book Seeker 代理增強檢索系統(SBS-AARS),一套由三個協同元件構成的新型多代理協作架構。其一,需求代理(User-Needs Agent)透過互動對話釐清模糊的檢索需求;其二,館員代理(Librarian Agent)建構並執行關鍵字檢索以取得候選書籍;其三,使用者代理(User Agent)作為具備領域知識的代理人,透過多輪討論與館員代理協作以評估並挑選最佳結果——此為彌補使用者常缺乏評估檢索結果專業能力的關鍵創新。於 20,000 本中文書籍上的實驗顯示,本系統較基線方法大幅提升:在前 5 筆結果達 87% 命中率與 57% 精確率,相較傳統關鍵字檢索分別提升 28% 與 90%,並在前 10 筆結果維持 55% 的精確率與召回率。結果證實多代理協作,尤其是以 LLM 代理作為使用者知識代理人,能有效克服圖書館書籍探索中的中介資料稀疏問題。 |
| 英文摘要 | Many libraries catalog books with titles alone, lacking rich metadata such as subject headings or abstracts. This metadata sparsity creates a cascade of retrieval challenges: users struggle to formulate effective queries without knowing exact titles, vocabulary mismatch causes relevant books to be missed, and users often lack domain expertise to evaluate whether retrieved results truly match their needs. To address these limitations, we propose the Smart Book Seeker Agent-Augmented Retrieval System for Metadata-Sparse Libraries (SBS-AARS), a novel multi-agent collaborative architecture comprising three coordinated components. First, a User-Needs Agent clarifies ambiguous search requirements through interactive dialogue. Second, a Librarian Agent formulates and executes keyword-based retrieval to obtain candidate books. Third, a User Agent acts as a domain-knowledge-equipped proxy that collaborates with the Librarian Agent through multi-turn discussions to evaluate and select optimal results—the key innovation that compensates for users' frequent lack of expertise in assessing retrieval outcomes. Experimental evaluation on 20,000 Chinese books demonstrates substantial improvements over baseline methods: our system achieves 87% hit rate and 57% precision at top-5 results, representing 28% and 90% relative improvements over traditional keyword-based retrieval, while maintaining 55% precision and recall at top-10 results. These findings validate that multi-agent collaboration, particularly the use of an LLM-based agent as a user's knowledge proxy, effectively overcomes metadata sparsity in library book discovery. |
| 發表成果與AI計畫研究主題相關性 | 本論文處理中介資料稀疏下的檢索難題。當資料只有零散標題、缺乏完整後設資料時,傳統關鍵字檢索容易失效,使用者也可能缺乏專業判斷結果是否合用。論文提出三代理協作架構,由需求代理釐清意圖、館員代理執行檢索、使用者代理作為知識代理人評估結果,在 20,000 筆資料上將前五筆精確率提升達 90%。農業現場常有類似情況,田間影像、感測紀錄與各來源文獻可能標註不全,基層使用者也不一定能自行判斷檢索結果。此架構有機會遷移到本中心農業知識庫,在中介資料不足時由代理協助補全意圖並評估結果,把較分散、描述不全的農業資料整合為可檢索、可評估的證據來源。 |