arXiv：cs.CL· Sourav Saha, Aditya Dutta, Soumajit Pramanik, Mandar Mitra·· 3 小时前AI 评分27
研究揭示查询扩展在信息检索中的性能差异成因
Towards Explaining Query Expansion Performance in Information Retrieval
AI 导读
研究从理想扩展查询（IEQ）和可分性两个角度解释查询扩展（QE）性能差异，并提出可分性度量及近似 IEQ 的实用公式。在 TREC Robust、TREC DL 2019-2022 passage 及 2019-2020 document 集合上的实验显示，与理想扩展查询越接近的扩展查询，检索效果越好；相关与非相关文档的可分性则提供了互补视角。
正文
Abstract:Query Expansion (QE) techniques have long been widely used in Information Retrieval (IR) to address the vocabulary mismatch problem. They remain relevant in modern retrieval systems, including those based on large language models (LLMs). However, no single QE method consistently outperforms others across all queries. This work seeks to explain the variation in QE performance through two complementary perspectives. The first is the concept of an Ideal Expanded Query (IEQ)--a hypothetical query that maximizes retrieval effectiveness with a downstream BM25 retrieval model. The second is a separability perspective, which quantifies how distinctly relevant and non-relevant documents are scored for a given expanded query using Cohen's (d). We develop a separability measure and practical formulations to approximate the IEQ and investigate how these factors relate to retrieval effectiveness. Extensive experiments on the TREC Robust collection, TREC DL 2019-2022 passage collections, and TREC DL 2019-2020 document collections reveal several interesting patterns. In particular, we find that expanded queries that are closer to the ideal expanded query tend to achieve higher retrieval effectiveness. We further show that the separability of relevant and non-relevant documents provides a complementary perspective for understanding QE performance.
| Subjects: | Information Retrieval (cs.IR); Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.09724 [cs.IR] |
| (or arXiv:2610.09724v1 [cs.IR] for this version) | |
| https://doi.org/10.48550/arXiv.2610.09724 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Sourav Saha [view email]
[v1]
Wed, 7 Oct 2026 09:21:17 UTC (1,190 KB)
来源：arXiv：cs.CL · arxiv.org