Skip to main content
Search

# Continuous Generative Retrieval

1 related articles

Subscribe to updates
  1. arXiv

    Multi-query retrieval stops duplicating itself: CACO coordinates sampled queries for complementary coverage, lifting Recall@100 by up to 23.7%

    Continuous generative retrievers sample several query vectors for one user and run parallel approximate nearest-neighbor search, but the queries often land in overlapping neighborhoods and waste a fixed retrieval budget. CACO is a lightweight self-supervised post-training framework that freezes the flow-matching or diffusion generator, uses retrieval frequencies of reference queries as a relevance proxy to build a label-free set-coverage objective, and trains a coordination network that adjusts the queries jointly. Across eight public benchmarks and an in-house 24-partition streaming industrial dataset, CACO raises Recall@100 by up to 23.7% and Recall@400 by up to 23.9% over the strongest baseline, cuts inter-query overlap by 53.3%–64.9%, and adds only 0.5%–3.0% inference latency.

You’re all caught up