用投票机制解决RAG中因错误检索引发的幻觉叠加问题。
Mitigating Hallucination on Hallucination in RAG via Ensemble Voting
- 多代理并行生成查询，聚合检索结果以降低偏差。
- 多个代理独立生成答案，通过多数表决确定最终输出。
- 无需训练、可并行处理，适合追求稳定性的实际应用。
检索增强生成（RAG）通过引入外部知识来减少大语言模型的幻觉，但其面临新挑战：‘幻觉上的幻觉’，即错误的检索结果误导生成模型，导致幻觉叠加。为此，我们提出VOTE-RAG，一种无需训练的两阶段框架，包含：(1) 检索投票，多个代理并行生成多样化查询，并聚合所有检索到的文档；(2) 响应投票，多个代理基于聚合文档独立生成答案，最终输出由多数票决定。我们在六个基准数据集上进行对比实验，结果表明VOTE-RAG性能与或优于更复杂的框架。此外，该方法架构简单、完全可并行化，且避免了‘问题漂移’风险。研究表明，简单的集成投票是缓解RAG幻觉的更优、更高效方案。
原文摘要 · Abstract (English)
Retrieval-Augmented Generation (RAG) aims to reduce hallucinations in Large Language Models (LLMs) by integrating external knowledge. However, RAG introduces a critical challenge: hallucination on hallucination," where flawed retrieval results mislead the generation model, leading to compounded hallucinations. To address this issue, we propose VOTE-RAG, a novel, training-free framework with a two-stage structure and efficient, parallelizable voting mechanisms. VOTE-RAG includes: (1) Retrieval Voting, where multiple agents generate diverse queries in parallel and aggregate all retrieved documents; (2) Response Voting, where multiple agents independently generate answers based on the aggregated documents, with the final output determined by majority vote. We conduct comparative experiments on six benchmark datasets. Our results show that VOTE-RAG achieves performance comparable to or surpassing more complex frameworks. Additionally, VOTE-RAG features a simpler architecture, is fully parallelizable, and avoids the problem drift" risk. Our work demonstrates that simple, reliable ensemble voting is a superior and more efficient method for mitigating RAG hallucinations.
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。