ArgRAG: Explainable Retrieval Augmented Generation using Quantitative Bipolar Argumentation
This addresses the need for explainable and contestable AI in high-stakes domains where noisy or contradictory evidence can lead to critical errors.
The paper tackled the problem of opaque and unreliable decision-making in Retrieval-Augmented Generation (RAG) systems by proposing ArgRAG, which uses a Quantitative Bipolar Argumentation Framework for structured inference, achieving strong accuracy on fact verification benchmarks like PubHealth and RAGuard.
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.