Mitigating KG Quality Issues: A Robust Multi-Hop GraphRAG Retrieval Framework
This addresses retrieval drift and hallucinations in multi-hop reasoning for AI systems using knowledge graphs, representing an incremental improvement with specific gains.
The paper tackles the problem of multi-hop reasoning in Graph Retrieval-Augmented Generation (GraphRAG) being hindered by imperfect knowledge graphs with quality issues like noise and incompleteness, proposing the C2RAG framework that improves performance by 3.4% EM and 3.9% F1 on average over baselines.
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.