Problem
Research questions and friction points this paper is trying to address.
multi-condition retrieval
query decomposition
retrieval pipeline
semantic dilution
reranking
When Should Queries Be Decomposed? A Stage-Aware Study of Query Decomposition for Multi-Condition Retrieval
🤖 AI Summary
This work addresses the unclear efficacy of query decomposition across different stages in multi-condition retrieval, where early-stage decomposition often leads to semantic dilution and degraded performance. Through empirical analysis, the study reveals that the effectiveness of query decomposition is highly stage-dependent and proposes the first stage-aware query decomposition framework. The approach preserves the full query during initial retrieval to maintain global semantics while introducing subqueries in the reranking stage to enable fine-grained constraint matching. Evaluated on the MultiConIR and SSRB benchmarks, this method significantly enhances the ranking performance of diverse retrieval and reranking models on compositional queries, effectively balancing semantic completeness with local constraint verification.
📝 Abstract
Multi-condition retrieval requires systems to identify documents that satisfy multiple distinct constraints, moving beyond mere topical relevance. While query decomposition is widely adopted as an intuitive remedy, its effectiveness across different retrieval pipeline stages remains underexplored. In this paper, we conduct a stage-aware empirical study and uncover a stark, stage-dependent effect: decomposition during initial retrieval frequently harms retrieval performance due to semantic dilution, yet substantially improves reranking by enabling more fine-grained constraint verification. Motivated by these insights, we propose a principled Stage-Aware Decomposition framework that retains the monolithic query during initial retrieval to preserve global semantic context, while employing sub-queries exclusively during reranking for fine-grained constraint matching. Extensive evaluations on the MultiConIR and SSRB benchmarks demonstrate that our framework consistently improves ranking performance for compositional queries across multiple retrieval and reranking models. We release our code at https://github.com/EIT-NLP/Query-Decompose.
Innovation
Methods, ideas, or system contributions that make the work stand out.
query decomposition
multi-condition retrieval
stage-aware framework
reranking
semantic dilution
🔎 Similar Papers
No similar papers found.
