用多方辩论机制解决RAG生成幻觉问题，提升事实准确性。
Removal of Hallucination on Hallucination: Debate-Augmented RAG
- 引入多智能体辩论机制，分阶段优化检索与生成
- 在多个任务上显著降低幻觉率，提升事实准确率
- 无需训练，适合需要高可信度生成的场景
检索增强生成（RAG）通过整合外部知识提升事实准确性，但错误或偏倚的检索会误导生成过程，导致幻觉叠加现象。为此，我们提出无需训练的辩论增强RAG（DRAG）框架，将多智能体辩论（MAD）机制融入检索与生成阶段。在检索阶段，通过支持者、反对者和裁判的结构化辩论，提升检索质量与事实可靠性；在生成阶段，引入非对称信息角色与对抗性辩论，增强推理鲁棒性，减少事实不一致。多项任务评估表明，DRAG有效提升检索可靠性，减少RAG引发的幻觉，并显著提高整体事实准确性。代码已开源。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。