Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This paper introduces RetrievalRouter, a novel query-aware routing mechanism that dynamically selects the optimal document retrieval pipeline based on the specific characteristics of each query. By leveraging a single tunable parameter, RetrievalRouter effectively navigates the trade-off between accuracy and latency, outperforming static baselines with a 2.5% increase in accuracy and a remarkable 12.4-fold improvement in speed. The results demonstrate that a tailored approach to retrieval can significantly enhance performance across various benchmarks in finance and scientific domains, challenging the notion that a one-size-fits-all pipeline is sufficient.
RetrievalRouter achieves a 2.5% accuracy boost while being 12.4 times faster than traditional static retrieval pipelines, revolutionizing how we approach document retrieval.
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.