RetrievalRouter：面向文档检索的联合模态与架构选择

摘要

文档检索日益支撑着金融、医疗和法律领域中的高风险信息获取。现代检索流水线在模态（文本或多模态）和检索架构（稠密检索或后期交互）两方面均存在差异。这些选择带来了一个难以两全的折衷：最有效的流水线在规模化运行时过于缓慢且成本高昂，而最快的流水线却无法从复杂文档中检索到证据。因此，实践者不得不在遗漏证据与不可用的延迟之间做出选择，且缺乏在查询层面自适应调整该选择的 principled 依据。我们证明这一折衷并非不可避免。并非每个查询都需要相同的流水线。在涵盖金融和科学语料库的多个基准测试中，没有任何静态流水线能够全面占优。我们提出了 RetrievalRouter，一种轻量级的查询感知路由器，它仅从查询文本本身学习哪种检索流水线最适合每个查询。一个可调节参数即可展现完整的精度-延迟前沿，并且对于每个静态基线，RetrievalRouter 都能提供一个同时具有更高精度和更低延迟的工作点。与最佳静态基线相比，RetrievalRouter 的精度提高了 2.5%，速度提升了 12.4 倍。此外，与先前的自适应策略选择方法相比，RetrievalRouter 在面向精度的设置中取得了显著更高的 nDCG@5，同时在面向延迟的设置中，其 nDCG@5 和延迟均达到或数值上超越现有方法。我们的代码和数据可在 https://github.com/emrekuruu/retrieval-router 获取。

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.