用统计方法保证RAG生成答案的可信度，无需真实答案
Response Quality Assessment for Retrieval-Augmented Generation via Conditional Conformal Factuality
- 基于置信区间预测原理，自动评估RAG回答中每个子结论的可靠性
- 在不依赖真实答案的情况下，保留60%更多高质量子结论
- 适合需要高可信度的复杂问答系统，如医疗或法律AI
现有RAG研究多关注整体问答准确率，常忽视生成回答中子结论的质量。现有自评估方法或缺乏概率保障，或需真实答案作为标注。为此，我们提出Conformal-RAG，受大语言模型上置信区间预测（CP）应用启发。该框架利用CP与RAG内部信息，在不需人工标注置信集的前提下，为多子领域提供分组条件覆盖的统计保证。实验表明，相比直接对LLM应用CP，Conformal-RAG在保持相同可靠性前提下，能多保留高达60%的高质量子结论，显著提升生成内容质量。
原文摘要 · Abstract (English)
Existing research on Retrieval-Augmented Generation (RAG) primarily focuses on improving overall question-answering accuracy, often overlooking the quality of sub-claims within generated responses. Recent methods that attempt to improve RAG trustworthiness, such as through auto-evaluation metrics, lack probabilistic guarantees or require ground truth answers. To address these limitations, we propose Conformal-RAG, a novel framework inspired by recent applications of conformal prediction (CP) on large language models (LLMs). Conformal-RAG leverages CP and internal information from the RAG mechanism to offer statistical guarantees on response quality. It ensures group-conditional coverage spanning multiple sub-domains without requiring manual labelling of conformal sets, making it suitable for complex RAG applications. Compared to existing RAG auto-evaluation methods, Conformal-RAG offers statistical guarantees on the quality of refined sub-claims, ensuring response reliability without the need for ground truth answers. Additionally, our experiments demonstrate that by leveraging information from the RAG system, Conformal-RAG retains up to 60\% more high-quality sub-claims from the response compared to direct applications of CP to LLMs, while maintaining the same reliability guarantee.
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。