# When Should Queries Be Decomposed? A Stage-Aware Study of Query Decomposition for Multi-Condition Retrieval

Source: [When Should Queries Be Decomposed? A Stage-Aware Study of Query Decomposition for Multi-Condition Retrieval](<https://www.sota2.com/research/paper/6a279e2390966ade919bf796>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-06-10T05:01:35.776Z

Authors: Bochao Yin, Xuan Lu, Zhengyu Qi, Xiaoyu Shen

Published: 2026-06-07T11:13:15.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Reranking on SSRB](<https://www.sota2.com/research/sota/reranking-on-ssrb.md>): Reranking; SSRB; NDCG@10 (Camera): 14.9.

- [Reranking on MultiConIR (test)](<https://www.sota2.com/research/sota/reranking-on-multiconir-test.md>): Reranking; MultiConIR (test); Q1 Score: 81.6.

- [Information Retrieval on SSRB](<https://www.sota2.com/research/sota/information-retrieval-on-ssrb.md>): Information Retrieval; SSRB; NDCG@10 (Camera): not recorded.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2606.08577>)

[PDF](<https://arxiv.org/pdf/2606.08577.pdf>)