RetrievalRouter：文件檢索中的聯合模態與架構選擇

摘要

文件檢索日益支撐金融、醫療保健與法律領域中高風險的資訊取得。現代檢索管線在模態（文字或多模態）與檢索架構（稠密或晚期交互）上各有不同。這些選擇構成了難以調和的取捨：最有效的管線在大規模運行時過於緩慢且昂貴，而最快的管線卻無法從複雜文件中檢出證據。因此，實務者必須在遺漏證據與無法使用的延遲之間做選擇，且缺乏在查詢層級調適此選擇的原則性依據。我們證明這種取捨並非必要。並非每個查詢都需要相同的管線。在涵蓋金融與科學語料的基準中，沒有任何靜態管線能全面勝出。我們提出 RetrievalRouter，一個輕量級的查詢感知路由器，僅從查詢文字本身學習哪條檢索管線最適合每個查詢。單一可調參數即可揭示完整的準確度-延遲前沿；而對每一條靜態基準管線，RetrievalRouter 都能提供一個同時更準確且更快的操作點。相較於最佳靜態基準，RetrievalRouter 的準確度提高 2.5%，速度快 12.4 倍。此外，與先前的自適應策略選擇方法相比，RetrievalRouter 在以準確度為導向的設定中取得顯著更高的 nDCG@5，而在以延遲為導向的設定中，其於 nDCG@5 與延遲兩方面均與之持平或數值上勝出。我們的程式碼與資料位於 https://github.com/emrekuruu/retrieval-router。

English

Document retrieval increasingly supports high-stakes information access in finance, healthcare, and law. Modern retrieval pipelines vary both in modality (text or multimodal) and in retrieval architecture (dense or late-interaction). These choices impose a hard compromise: the most effective pipelines are too slow and expensive to run at scale, while the fastest fail to retrieve evidence from complex documents. Practitioners must therefore choose between missed evidence and unusable latency, with no principled basis for adapting that choice at the query level. We show that this compromise is unnecessary. Not every query requires the same pipeline. Across benchmarks spanning financial and scientific corpora, no static pipeline dominates. We introduce RetrievalRouter, a lightweight query-aware router that learns, from the query text alone, which retrieval pipeline best fits each query. A single tunable parameter exposes the full accuracy-latency frontier, and for every static baseline, RetrievalRouter offers an operating point that is simultaneously more accurate and faster. Against the best static baseline, RetrievalRouter is 2.5% more accurate and 12.4 times faster. Furthermore, compared with prior adaptive strategy selection methods, RetrievalRouter achieves significantly higher nDCG@5 across accuracy-oriented settings, while matching or numerically outperforming them on both nDCG@5 and latency in latency-oriented settings. Our code and data are available at https://github.com/emrekuruu/retrieval-router.