Removal of Hallucination on Hallucination: Debate-Augmented RAG
This addresses a critical issue in RAG systems for AI applications where factual accuracy is essential, representing an incremental improvement through a novel framework.
The paper tackles the problem of hallucinations in Retrieval-Augmented Generation (RAG) caused by erroneous retrieval, proposing Debate-Augmented RAG (DRAG) to improve factual accuracy. Results show DRAG reduces RAG-induced hallucinations and enhances retrieval reliability across multiple tasks.
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 at https://github.com/Huenao/Debate-Augmented-RAG.