用RAG和多模型辩论减少大模型在因果发现中的幻觉
A Novel Approach to Eliminating Hallucinations in Large Language Model-Assisted Causal Discovery
- 引入RAG和多模型辩论机制降低幻觉
- 多模型辩论效果接近RAG，且无需高质量数据
- 首次系统评估主流大模型在因果发现中的幻觉问题
大型语言模型在因果发现中替代领域专家的使用日益增多，凸显出模型选择的重要性。本文首次对主流大模型在因果发现中的幻觉现象进行了系统调查。研究发现，使用大模型进行因果发现时存在显著幻觉，因此模型选择至关重要。当有高质量数据可用时，我们提出采用检索增强生成（RAG）来降低幻觉。此外，我们引入一种新方法：通过多个大模型在仲裁者监督下辩论因果图中的边，实现与RAG相当的幻觉抑制效果。
原文摘要 · Abstract (English)
The increasing use of large language models (LLMs) in causal discovery as a substitute for human domain experts highlights the need for optimal model selection. This paper presents the first hallucination survey of popular LLMs for causal discovery. We show that hallucinations exist when using LLMs in causal discovery so the choice of LLM is important. We propose using Retrieval Augmented Generation (RAG) to reduce hallucinations when quality data is available. Additionally, we introduce a novel method employing multiple LLMs with an arbiter in a debate to audit edges in causal graphs, achieving a comparable reduction in hallucinations to 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。