Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat
Sign Up
Cited by 18

The DOI matches its Crossref record; 33 of the 33 references it cites were found in a registry or an index.

MultiRAG: A Knowledge-Guided Framework for Mitigating Hallucination in Multi-Source Retrieval Augmented Generation

Wu, Wenlong, Wang, Haofen, Li, Bohan, Huang, Peixuan, Zhao, Xinzhe, Liang, Lei·2025·2025 IEEE 41st International Conference on Data Engineering (ICDE)
DOI 10.1109/icde65448.2025.00230
Open this paper in CoChat — free account

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.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/icde65448.2025.00230

Cites

33 of 33 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Research works printed but not linked: 19

  1. Ouyang, 2022, Training language models to follow instructions with human feedback, Advances in neural information processing systems, 35, 27730
  2. Lewis, 2020, Retrieval-augmented generation for knowledge-intensive nlp tasks, Advances in Neural Information Processing Systems, 33, 9459
  3. Guu, 2020, Retrieval augmented language model pre-training, 3929
  4. Gao, 2023, Retrieval-augmented generation for large language models: A survey, arXiv preprint, 2
  5. Izacard, 2020, Leveraging passage retrieval with generative models for open domain question answering, arXiv preprint
  6. Izacard, 2022, Few-shot learning with retrieval augmented language models, arXiv preprint, 2
  7. Lewis, 2020, Retrieval-augmented generation for knowledge-intensive nlp tasks, Advances in Neural Information Processing Systems, 33, 9459
  8. Wu, 2025, A cross-domain heterogeneous data query framework via collaboration of large language models and knowledge graphs, Journal of Computer Research and Development, 62, 605
  9. Wang, 2024, Large language models-guided dynamic adaptation for temporal knowledge graph reasoning, arXiv preprint
  10. Luo, 2023, Reasoning on graphs: Faithful and interpretable large language model reasoning, arXiv preprint
  11. Gutiérrez, 2024, Hipporag: Neurobiologically inspired long-term memory for large language models, arXiv preprint
  12. Mavromatis, 2024, Gnn-rag: Graph neural retrieval for large language model reasoning, arXiv preprint
  13. Gao, 2025, U-niah: Unified rag and llm evaluation for long context needle-in-a-haystack, arXiv preprint
  14. Zhang, 2021, Evaluation of knowledge credibility based on knowledge representation learning, Computer Engineering, 47, 44
  15. Wei, 2022, Chain-of-thought prompting elicits reasoning in large language models, Advances in neural information processing systems, 35, 24824
  16. Trivedi, 2022, Interleaving retrieval with chain-of-thought reasoning for knowledge-intensive multi-step questions, ArXiv, abs/2212.10509 · arXiv
  17. 10.1609/aaai.v38i17.29889 · DOI
  18. Chan, 2024, Rq-rag: Learning to refine queries for retrieval augmented generation, arXiv preprint
  19. Hu, 2024, Refchecker: Reference-based fine-grained hallucination checker and benchmark for large language models, arXiv preprint

Metadata

Authors
Wu, W., Wang, H., Li, B., Huang, P., Zhao, X., & Liang, L.
Venue
2025 IEEE 41st International Conference on Data Engineering (ICDE)
Publisher
IEEE
Published
2025-05-19
Pages
3070-3083
DOI
10.1109/icde65448.2025.00230
Cited by
18
References
33
Licence

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.