# ArgRAG: Explainable Retrieval Augmented Generation using Quantitative Bipolar Argumentation

## TL;DR

ArgRAG introduces a structured, explainable reasoning framework for retrieval-augmented generation, improving transparency and contestability in high-stakes applications by replacing black-box models with deterministic argumentation.

## Contribution

It presents ArgRAG, a novel method that uses a Quantitative Bipolar Argumentation Framework for transparent reasoning in RAG systems, addressing limitations of noise sensitivity and opacity.

## Key findings

- Achieves strong accuracy on PubHealth and RAGuard benchmarks.
- Significantly improves transparency and explainability.
- Provides a contestable reasoning process for high-stakes domains.

## Abstract

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.