Graph Retrieval-Augmented Generation enhances multi-hop reasoning but relies on imperfect knowledge graphs that frequently suffer from inherent quality issues. Current approaches often overlook these issues, consequently struggling with retrieval drift driven by spurious noise and retrieval hallucinations stemming from incomplete information. To address these challenges, we propose C2RAG (Constraint-Checked Retrieval-Augmented Generation), a framework aimed at robust multi-hop retrieval over the imperfect KG. First, C2RAG performs constraint-based retrieval by decomposing each query into atomic constraint triples, with using fine-grained constraint anchoring to filter candidates for suppressing retrieval drift. Second, C2RAG introduces a sufficiency check to explicitly prevent retrieval hallucinations by deciding whether the current evidence is sufficient to justify structural propagation, and activating textual recovery otherwise. Extensive experiments on multi-hop benchmarks demonstrate that C2RAG consistently outperforms the latest baselines by 3.4\% EM and 3.9\% F1 on average, while exhibiting improved robustness under KG issues.

翻译：图检索增强生成技术虽然能够增强多跳推理能力，但其依赖于存在固有质量缺陷的不完美知识图谱。现有方法往往忽视这些问题，因而难以应对由虚假噪声导致的检索漂移以及信息不完整引发的检索幻觉。为应对这些挑战，我们提出C2RAG（约束校验检索增强生成框架），该框架旨在实现不完美知识图谱上的鲁棒多跳检索。首先，C2RAG通过将每个查询分解为原子约束三元组进行基于约束的检索，利用细粒度约束锚定筛选候选实体以抑制检索漂移。其次，C2RAG引入充分性校验机制，通过判定当前证据是否足以支撑结构传播来显式防止检索幻觉，否则将激活文本恢复模块。在多跳基准测试上的大量实验表明，C2RAG在EM指标上平均超越最新基线方法3.4%，在F1指标上平均提升3.9%，同时在知识图谱缺陷条件下展现出更强的鲁棒性。