提出新方法精准识别RAG生成内容的幻觉，区分事实错误与证据不符。
Faithfulness-Aware Uncertainty Quantification for Fact-Checking the Output of Retrieval Augmented Generation
- 分两路量化不确定性：一边看是否符合检索证据，一边看是否事实正确
- 在多数据集上检测事实错误的准确率优于现有方法
- 适合需要高可信度问答系统的研究人员和开发者
增强检索的大语言模型（RAG）在开放域问答中表现优异，但仍易产生幻觉：错误信息可能源于模型内部知识或检索内容的不准确。现有方法常混淆事实性与对检索证据的忠实性，若陈述未被检索内容明确支持，即使事实正确也会被误判为幻觉。本文提出FRANQ，一种新的幻觉检测方法，通过分别对事实性和证据忠实性应用不确定性量化（UQ）技术进行评估。为验证FRANQ及对比方法，我们构建了一个新长文本问答数据集，标注了事实性与忠实性，结合自动化标注与人工校验难例。在多个数据集、任务和大模型上的大量实验表明，FRANQ在检测RAG输出中的事实错误方面显著优于现有方法。
原文摘要 · Abstract (English)
Large Language Models (LLMs) enhanced with retrieval, an approach known as Retrieval-Augmented Generation (RAG), have achieved strong performance in open-domain question answering. However, RAG remains prone to hallucinations: factually incorrect outputs may arise from inaccuracies in the model's internal knowledge and the retrieved context. Existing approaches to mitigating hallucinations often conflate factuality with faithfulness to the retrieved evidence, incorrectly labeling factually correct statements as hallucinations if they are not explicitly supported by the retrieval. In this paper, we introduce FRANQ, a new method for hallucination detection in RAG outputs. FRANQ applies distinct uncertainty quantification (UQ) techniques to estimate factuality, conditioning on whether a statement is faithful to the retrieved context. To evaluate FRANQ and competing UQ methods, we construct a new long-form question answering dataset annotated for both factuality and faithfulness, combining automated labeling with manual validation of challenging cases. Extensive experiments across multiple datasets, tasks, and LLMs show that FRANQ achieves more accurate detection of factual errors in RAG-generated responses compared to existing approaches.
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。