发表机构
ETH Zurich; Agentic Systems Lab; Norwegian University of Science and Technology（苏黎世联邦理工学院; 智能体系统实验室; 挪威科技大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
ConRAG通过构建轻量级实体-文档图并执行端点约束的路径检索，高效推断多跳关系，在MuSiQue和2WikiMultiHopQA上提升桥梁实体与推理链恢复，并大幅降低索引成本。
AI 中文摘要
理解两个实体如何关联，通常需要跨文档追踪多跳关系，以识别连接它们的中间实体和支持性证据。这一任务在科学研究及其他知识密集型分析中频繁出现。我们将此场景形式化为多跳关系推断：给定两个已知的端点实体，目标是恢复连接它们的桥梁实体及基于证据的推理链，跨越文档语料库，并生成基于所检索证据的解释。现有的多跳RAG系统通常寻求一个未知的答案实体，而非显式恢复两个已知端点之间的连接，而基于图的方法往往依赖成本高昂的LLM抽取知识图谱，限制了其在大规模文档集合上的可扩展性。我们引入ConRAG，它通过实体共现和基于LLM的实体过滤构建轻量级的实体-文档图。其连接性检索推断并语义排序两个端点之间的路径。在MuSiQue和2WikiMultiHopQA上，ConRAG在桥梁实体和推理链恢复方面持续优于强RAG基线，同时将图索引的令牌成本降低约1.5个数量级。我们的结果表明，端点约束的路径检索为基于证据的关系发现提供了一种有效且索引高效的方法。
英文摘要
Understanding how two entities are connected often requires tracing multi-hop relations across documents to identify intermediate entities and supporting evidence that explain a connection. This is a task that appears frequently in scientific research and other knowledge-intensive analyses. We formalise this setting as multi-hop relation inference: given two known endpoint entities, we aim to recover the bridge entities and evidence-grounded reasoning chains that connect them across a document corpus, and to generate an explanation grounded in the retrieved evidence. Existing multi-hop RAG systems typically seek an unknown answer entity rather than explicitly recovering the connection between two known endpoints and graph-based approaches often rely on costly LLM-extracted knowledge graphs that limit scalability to large document collections. We introduce ConRAG, which builds a lightweight entity-document graph from entity co-occurrence and LLM-based entity filtering. Its connective retrieval infers and semantically ranks paths between two endpoints. On MuSiQue and 2WikiMultiHopQA, ConRAG consistently improves bridge entity and reasoning chain recovery over strong RAG baselines, while reducing graph-indexing token cost by up to roughly 1.5 orders of magnitude. Our results show that endpoint-constrained path retrieval provides an effective and index-efficient approach to evidence-grounded relation discovery.
