用量化双极论证框架提升RAG的可解释性与可信度
ArgRAG: Explainable Retrieval Augmented Generation using Quantitative Bipolar Argumentation
- 引入量化双极论证框架，将检索内容转化为结构化推理证据
- 在PubHealth和RAGuard上实现高准确率，决策过程可解释
- 适合需要透明决策的医疗、法律等高风险领域
检索增强生成（RAG）通过引入外部知识增强大模型能力，但在高风险场景中存在对噪声或矛盾信息敏感、决策过程不透明等问题。本文提出ArgRAG，一种可解释且可质疑的替代方案，采用定量双极论证框架（QBAF）替代黑箱推理。ArgRAG从检索文档构建QBAF，基于渐进语义进行确定性推理，可忠实解释并反驳决策。在PubHealth和RAGuard两个事实验证基准上评估，ArgRAG不仅保持较高准确率，还显著提升透明度。
原文摘要 · Abstract (English)
Retrieval-Augmented Generation (RAG) enhances large language models by incorporating external knowledge, yet suffers from critical limitations in high-stakes domains -- namely, sensitivity to noisy or contradictory evidence and opaque, stochastic decision-making. We propose ArgRAG, an explainable, and contestable alternative that replaces black-box reasoning with structured inference using a Quantitative Bipolar Argumentation Framework (QBAF). ArgRAG constructs a QBAF from retrieved documents and performs deterministic reasoning under gradual semantics. This allows faithfully explaining and contesting decisions. Evaluated on two fact verification benchmarks, PubHealth and RAGuard, ArgRAG achieves strong accuracy while significantly improving transparency.
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。