查询分解时机影响检索效果，初期不宜拆分，重排时才有效。
When Should Queries Be Decomposed? A Stage-Aware Study of Query Decomposition for Multi-Condition Retrieval
- 初始检索保留完整查询，避免语义稀释
- 重排阶段使用子查询精准匹配约束条件
- 在多个模型上提升组合查询的排序性能
多条件检索要求系统识别满足多个独立约束的文档，超越单纯的主题相关性。尽管查询分解被广泛视为直观解决方案，但其在不同检索阶段的有效性仍缺乏研究。本文通过阶段感知的实证研究发现：在初始检索阶段进行分解常因语义稀释而损害性能，而在重排阶段则显著提升精度，实现更细粒度的约束验证。基于此，我们提出一种原则性的阶段感知分解框架：在初始检索中保持查询整体性以保留全局语义，仅在重排阶段使用子查询进行精细匹配。在MultiConIR和SSRB基准上的大量实验表明，该框架能持续提升多种检索与重排模型对组合查询的排序表现。代码已开源：https://github.com/EIT-NLP/Query-Decompose。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。