提出新框架缓解知识图谱缺陷导致的检索漂移与幻觉。
Toward Robust GraphRAG: Mitigating Retrieval Drift and Hallucination from Imperfect Knowledge Graphs
- 通过原子约束规划与细粒度检索，精准定位推理路径。
- 在三个多跳问答数据集上显著降低对知识图谱构建器的依赖。
- 支持结构不足时文本恢复，避免错误推理延续。
图检索增强生成（GraphRAG）通过将知识图谱（KG）作为结构化检索索引，成为多跳推理的常用方法。然而，现有方法隐含假设大语言模型构建的知识图谱能有效支撑证据链。我们通过实证分析发现，这一假设在实践中并不总成立，识别出两类被忽视的图谱问题：虚假噪声与信息不全。虚假噪声导致检索偏离至看似合理但无依据的三元组，信息不全则迫使模型在支撑不足的图结构中继续推断，引发检索幻觉。为此，我们提出CS-RAG，一种鲁棒的GraphRAG框架，通过在检索阶段缓解不完美知识图谱的影响，而非依赖图谱修复。CS-RAG首先将每个查询规划为可执行的原子约束序列，并进行细粒度的锚点与关系感知检索，以约束证据获取的语义边界。随后通过充分性检查判断已检索证据是否足以安全绑定变量供后续传播；当结构支持不足时，激活文本恢复机制，从而减少幻觉式结构延续。在三个多跳问答基准上的实验表明，CS-RAG对知识图谱构建器的选择更不敏感，且在可控注入图谱缺陷条件下仍保持稳定。代码已开源：https://github.com/myz12138/CS-RAG/
原文摘要 · Abstract (English)
Graph Retrieval-Augmented Generation (GraphRAG) has become a common approach for multi-hop reasoning by using knowledge graphs (KGs) as structured retrieval indexes. However, most existing GraphRAG methods implicitly assume that LLM-constructed KGs provide structural support for evidence chaining. In this paper, we show that this assumption does not always hold in practice through an empirical analysis, and identify two recurring KG issue modes often overlooked by current retrievers: spurious noise and incomplete information. Spurious noise induces retrieval drift toward plausible but unsupported triples, whereas incomplete information leads to retrieval hallucination by forcing continuation through under-supported graph structure. To address these challenges, we propose CS-RAG, a robust GraphRAG framework that mitigates the impact of imperfect KGs during retrieval rather than relying on KG repair. 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 the retrieved evidence can safely induce variable bindings for subsequent propagation and activates textual recovery when structural support is insufficient, 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/
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。