通过分组导航提升证据检索，解决传统方法召回率低的问题
Group-Aware Adaptive Retrieval for Evidence Navigation
- 将文档按语义关联分组，从组级而非单文档层面扩展候选集
- 在BRIGHT数据集上相比最强基线提升8.0%的检索准确率
- 适合需要深度推理的复杂查询场景，如科学问答与事实验证
推理型检索针对仅靠表面匹配无法判断相关性的查询，需多步推理。由于相关文档常不在初始候选集中，现有系统面临召回受限问题。现有方法在语料图上逐文档迭代扩展，孤立考察邻居，易陷入语料局部区域。为此，我们提出面向证据导航的分组感知自适应检索方法（GAREN），通过组级扩展探索语料图。GAREN基于文档在语料图中的连接关系，将文档组织成语义一致且可区分的组，每组信息指示其扩展后可访问的内容，提供超越单文档信号的引导。每轮迭代中，GAREN使用组级导航器识别有潜力的扩展方向，从选定组中检索文档，并用文档级重排序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最高提升8.0%。源代码已开源：https://github.com/KJ12124/GAREN
原文摘要 · Abstract (English)
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
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。