arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.14828cs.IR
收藏

迈向稳健的GraphRAG:减轻不完美知识图谱中的检索漂移和幻觉

Don't Worry About Quality: Robust Multi-Hop Retrieval despite Issues in Knowledge Graphs

University of Electronic Science and Technology of China(电子科技大学)

Yizhuo Ma, Ke Qin, Jinchuan Xu, Tao Wen, Rongzheng Wang, Jiakai Li, Nan Chen, Lunxu Liu, Deqiang Ouyang, Shuang Liang, Man-Fai Leung

AI总结:

本文针对GraphRAG中因知识图谱不完美导致的检索漂移和幻觉问题,提出CS-RAG框架,通过精细化检索和充分性检查来减少不准确的证据延续。

摘要:

Graph Retrieval-Augmented Generation (GraphRAG) 已成为通过使用知识图谱 (KGs) 作为结构化检索索引进行多跳推理的常见方法。然而,大多数现有的GraphRAG方法隐式假设LLM构建的KGs为证据链提供结构支持。在本文中,我们通过实证分析表明,这一假设在实践中并不总是成立,并识别出两种常被现有检索器忽视的KG问题模式:虚假噪声和信息不完整。虚假噪声导致检索漂向合理但不支持的三元组,而信息不完整则通过强制延续未支持的图结构导致检索幻觉。为了解决这些挑战,我们提出CS-RAG,一个稳健的GraphRAG框架,通过在检索过程中减轻不完美KGs的影响,而不是依赖KG修复。CS-RAG首先将每个查询规划为一个可执行原子约束的有序序列,并执行细粒度的锚点和关系感知检索,以约束证据获取在预期的跳转语义周围。然后应用充分性检查以决定检索到的证据是否能安全地诱导变量绑定用于后续传播,并在结构支持不足时激活文本恢复,从而减少幻觉的结构延续。在三个多跳QA基准测试中的实验表明,CS-RAG对构建者选择的敏感性较低,并在受控的KG问题注入下保持稳定。代码可在:https://github.com/myz12138/CS-RAG/

英文摘要:

Graph Retrieval-Augmented Generation (GraphRAG) has made substantial progress in multi-hop reasoning, but typically assumes that constructed knowledge graphs (KGs) provide sufficient structural support. In practice, cost and computing constraints often leave constructed KGs imperfect, raising the key challenge of achieving robust multi-hop retrieval. To address this challenge, we empirically analyze KG extraction across builders and find similar error patterns despite differences in error proportions, motivating a retrieval strategy targeted at these shared errors. We further summarize these patterns into two issue modes, spurious noise and incomplete information, which induce retrieval drift and retrieval hallucination by misleading evidence selection and weakening evidential support, respectively. Based on this, we propose CS-RAG, a robust GraphRAG framework that mitigates the impact of imperfect KGs during retrieval. CS-RAG first plans each query as an ordered sequence of executable atomic constraints and performs fine-grained anchor- and relation-aware retrieval to constrain evidence acquisition around the intended hop semantics. It then applies a sufficiency check to decide whether retrieved entities should serve as anchors for subsequent retrieval hops and activates textual recovery for unresolved constraints, thereby reducing hallucinated structural continuation. Experiments on three multi-hop QA benchmarks show that CS-RAG is less sensitive to builder choice and remains stable under controlled KG issue injection. Code is available at https://github.com/myz12138/CS-RAG.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑