Mitigating KG Quality Issues: A Robust Multi-Hop GraphRAG Retrieval Framework

2026-03-16

AI Summary

This work addresses the challenges of retrieval drift and hallucination in multi-hop question answering caused by noise and missing information in knowledge graphs. To mitigate these issues, the authors propose the C2RAG framework, which employs fine-grained constraint anchoring to suppress retrieval drift and integrates a structure-aware sufficiency verification mechanism to alleviate hallucinations stemming from incomplete knowledge. The approach synergistically combines constraint decomposition, textual reconstruction, and a GraphRAG architecture. Evaluated on multiple multi-hop QA benchmarks, C2RAG achieves an average improvement of 3.4% in Exact Match (EM) and 3.9% in F1 score over state-of-the-art methods, while demonstrating enhanced robustness when operating with low-quality knowledge graphs.

Technology Category

• Knowledge Representation and Reasoning: Computational Complexity of Reasoning
• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories
• Data Mining & Knowledge Management: Linked Open Data, Knowledge Graphs & KB Completion

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies

Abstract

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.

Problem

• knowledge graph quality
• retrieval drift
• retrieval hallucination
• multi-hop reasoning
• imperfect knowledge graphs

Innovation

• Constraint-Based Retrieval
• Retrieval Hallucination
• Multi-Hop Reasoning
• Knowledge Graph Quality
• GraphRAG