MultiRAG: A Knowledge-Guided Framework for Mitigating Hallucination in Multi-Source Retrieval Augmented Generation
Authors:
- 19 May 2025
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 3070-3083
Abstract
Retrieval Augmented Generation (RAG) has emerged as a promising solution to address hallucination issues in Large Language Models (LLMs). However, the integration of multiple retrieval sources, while potentially more informative, introduces new challenges that can paradoxically exacerbate hallucination problems. These challenges manifest primarily in two aspects: the sparse distribution of multi-source data that hinders the capture of logical relationships and the inherent inconsistencies among different sources that lead to information conflicts. To address these challenges, we propose MultiRAG, a novel framework designed to mitigate hallucination in multi-source retrieval-augmented generation through knowledge-guided approaches. Our framework introduces two key innovations: (1) a knowledge construction module that employs multi-source line graphs to efficiently aggregate logical relationships across different knowledge sources, effectively addressing the sparse data distribution issue; and (2) a sophisticated retrieval module that implements a multi-level confidence calculation mechanism, performing both graph-level and node-level assessments to identify and eliminate unreliable information nodes, thereby reducing hallucinations caused by inter-source inconsistencies. Extensive experiments on four multi-domain query datasets and two multi-hop QA datasets demonstrate that MultiRAG significantly enhances the reliability and efficiency of knowledge retrieval in complex multi-source scenarios. Our code is available in https://github.com/wuwenlong123/MultiRAG.Keywords
All Related Versions
This publication has 27 references indexed in Scilit:
- Large Language Model Enhanced Knowledge Representation Learning: A SurveyData Science and Engineering, 2025
- HyCubE: Efficient Knowledge Hypergraph 3D Circular Convolutional EmbeddingIEEE Transactions on Knowledge and Data Engineering, 2025
- Metacognitive Retrieval-Augmented Large Language Models2024
- Scalable and Effective Generative Information Retrieval2024
- Decoupling Anomaly Discrimination and Representation Learning: Self-supervised Learning for Anomaly Detection on Attributed GraphData Science and Engineering, 2024
- Leveraging Semantic Information for Enhanced Community Search in Heterogeneous GraphsData Science and Engineering, 2024
- HJE: Joint Convolutional Representation Learning for Knowledge Hypergraph CompletionIEEE Transactions on Knowledge and Data Engineering, 2024
- Unifying Large Language Models and Knowledge Graphs: A RoadmapIEEE Transactions on Knowledge and Data Engineering, 2024
- Domain-aware multi-truth discovery from conflicting sourcesProceedings of the VLDB Endowment, 2018
- Truth discovery with multiple conflicting information providers on the web2007