Removal of Hallucination on Hallucination: Debate-Augmented RAG

TL;DR

This paper introduces Debate-Augmented RAG (DRAG), a novel framework that uses multi-agent debates during retrieval and generation to reduce hallucinations and improve factual accuracy in retrieval-augmented generation systems.

Contribution

DRAG is a training-free method that integrates structured debates into RAG, enhancing retrieval quality and factual reliability without additional training.

Findings

DRAG reduces hallucinations in RAG outputs.

DRAG improves factual accuracy across multiple tasks.

Debate mechanisms enhance retrieval and reasoning robustness.

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 at https://github.com/Huenao/Debate-Augmented-RAG.