Directional feedback improves search queries for better retrieval results
Directional Posterior Feedback Fusion for Query Reformulation in Dense Retrieval
Information Retrieval
Summary
Short or unclear search queries often make it hard for computers to find the right answers. The authors show a new method that improves these queries by using feedback differently. Instead of mixing feedback as single fixed points, their approach treats feedback as directions that guide how to change the query. This leads to better search results without needing to retrain the search system. Their tests show that this new way of using feedback works better than older methods across various search setups.
What this means in practice
- •For search engine engineers: Improve query understanding by refining search queries using directional feedback to boost retrieval accuracy without retraining models.
- •For digital library developers: Enhance search results in large digital collections by applying directional feedback fusion to better capture user intent in vague queries.
Authors
Yiteng Tu, Qingyi Pan, Weihang Su, Jiaxin Mao, Yiqun Liu, Qingyao Ai
Abstract
Dense retrieval has become a fundamental paradigm for modern information retrieval, supporting efficient semantic search across a wide range of applications. Its effectiveness, however, relies critically on query embeddings that adequately capture users' information needs, which can be difficult for short, ambiguous, or underspecified queries. Feedback-based query reformulation approaches like pseudo-relevance feedback (PRF) alleviate this by incorporating additional evidence from retrieved or generated content. However, existing embedding-space approaches commonly aggregate or interpolate feedback vectors, implicitly treating them as complete target representations. Such pointwise fusion can unnecessarily suppress query corrections along directions not expressed by individual feedback items, even when these directions are supported by complementary evidence. To address this limitation, we propose Directional Posterior Feedback Fusion (DIFF), a query reformulation framework that models feedback as directional evidence rather than target points. DIFF represents feedback as confidence-weighted directional evidence in the tangent space of the original query and jointly infers a controlled query update through prior-regularized posterior fusion, without retraining the underlying dense retriever. Experiments across multiple dense retrievers and different feedback sources show that DIFF achieves the best overall retrieval performance, demonstrating the effectiveness of explicitly modeling how feedback should constrain query updates.