幻觉叠加幻觉的消除：辩论增强型检索增强生成
Removal of Hallucination on Hallucination: Debate-Augmented RAG
AI总结：
针对RAG中错误检索导致幻觉叠加的问题，提出辩论增强型RAG（DRAG），通过多智能体辩论优化检索与生成，提升事实准确性并减少幻觉。
摘要：
检索增强生成（RAG）通过整合外部知识来提升事实准确性，但同时也引入了一个关键问题：错误或有偏见的检索可能误导生成过程，加剧幻觉现象，我们将其称为“幻觉叠加幻觉”。为解决这一问题，我们提出了辩论增强型检索增强生成（DRAG），这是一种无需训练的框架，将多智能体辩论（MAD）机制整合到检索和生成两个阶段。在检索阶段，DRAG采用支持者、反对者和裁判之间的结构化辩论来优化检索质量并确保事实可靠性。在生成阶段，DRAG引入不对称信息角色和对抗性辩论，增强推理鲁棒性并减少事实不一致。跨多个任务的评估表明，DRAG提升了检索可靠性，减少了RAG引发的幻觉，并显著提高了整体事实准确性。我们的代码可在https://github.com/Huenao/Debate-Augmented-RAG获取。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
