发表机构
Sungkyunkwan University（成均馆大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对推理密集型检索的召回率受限问题，提出GAREN方法，通过组级扩展探索语料库图，在BRIGHT数据集上较最强基线提升达8.0%。
AI 中文摘要
推理密集型检索针对那些无法通过表面匹配识别相关性、需要多步推理的查询。由于相关文档很少出现在初始候选集中，检索系统会面临召回率受限的问题。现有方法在语料库图上以文档级别的方式迭代扩展候选池，孤立地检查每个邻居，容易漂移到语料库的狭窄区域。为解决该问题，本文提出面向证据导航的组感知自适应检索（GAREN），该方法通过组级扩展探索语料库图。GAREN根据文档在语料库图中的连接关系，将其组织成语义连贯且可区分的组，每个组的信息能指示通过该组扩展可获取的内容，提供超出单个文档级信号的指导。在每次迭代中，GAREN使用组级导航器识别有前景的扩展方向，从选中的组中检索文档，并应用文档级重排器评估更新后的候选集。大量实验表明，GAREN在BRIGHT数据集上相比最强基线实现了高达8.0%的提升，源代码可在此URL获取。
英文摘要
Reasoning-intensive retrieval addresses queries whose relevance cannot be identified by surface-level matching, thereby requiring multi-step reasoning. Because relevant documents rarely appear in the initial candidate set, retrieval systems suffer from the bounded recall problem. Existing methods iteratively expand a candidate pool at the document level over a corpus graph, examining each neighbor in isolation and drifting toward a narrow region of the corpus. To address this problem, we propose Group-Aware Adaptive Retrieval for Evidence Navigation (GAREN), which explores the corpus graph through group-level expansion. GAREN organizes documents into semantically coherent and distinguishable groups based on their connections in the corpus graph. The information in each group indicates what can be accessed by expanding through it, providing guidance beyond individual document-level signals. At each iteration, GAREN uses a group-level navigator to identify promising expansion directions, retrieves documents from the selected groups, and applies a document-level reranker to evaluate the updated candidate set. Extensive experiments show that GAREN achieves up to 8.0% improvement over the strongest baseline on BRIGHT. The source code is available at https://github.com/KJ12124/GAREN
CommentsAccepted to EMNLP 2026; 20 pages, 11 figures, 13 tables
