ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2505.18581
51
0

Removal of Hallucination on Hallucination: Debate-Augmented RAG

24 May 2025
Wentao Hu
Wengyu Zhang
Yiyang Jiang
C. Zhang
Xiaoyong Wei
Qing Li
ArXiv (abs)PDFHTML
Main:8 Pages
6 Figures
Bibliography:3 Pages
6 Tables
Appendix:4 Pages
Abstract

Retrieval-Augmented Generation (RAG) enhances factual accuracy by integrating external knowledge, yet it introduces a critical issue: erroneous or biased retrieval can mislead generation, compounding hallucinations, a phenomenon we term Hallucination on Hallucination. To address this, we propose Debate-Augmented RAG (DRAG), a training-free framework that integrates Multi-Agent Debate (MAD) mechanisms into both retrieval and generation stages. In retrieval, DRAG employs structured debates among proponents, opponents, and judges to refine retrieval quality and ensure factual reliability. In generation, DRAG introduces asymmetric information roles and adversarial debates, enhancing reasoning robustness and mitigating factual inconsistencies. Evaluations across multiple tasks demonstrate that DRAG improves retrieval reliability, reduces RAG-induced hallucinations, and significantly enhances overall factual accuracy. Our code is available atthis https URL.

View on arXiv
@article{hu2025_2505.18581,
  title={ Removal of Hallucination on Hallucination: Debate-Augmented RAG },
  author={ Wentao Hu and Wengyu Zhang and Yiyang Jiang and Chen Jason Zhang and Xiaoyong Wei and Qing Li },
  journal={arXiv preprint arXiv:2505.18581},
  year={ 2025 }
}
Comments on this paper