Enregistré dans:
Détails bibliographiques
Auteurs principaux: Zhu, Yuqicheng, Potyka, Nico, Hernández, Daniel, He, Yuan, Ding, Zifeng, Xiong, Bo, Zhou, Dongzhuoran, Kharlamov, Evgeny, Staab, Steffen
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2508.20131
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866918131811745792
author Zhu, Yuqicheng
Potyka, Nico
Hernández, Daniel
He, Yuan
Ding, Zifeng
Xiong, Bo
Zhou, Dongzhuoran
Kharlamov, Evgeny
Staab, Steffen
author_facet Zhu, Yuqicheng
Potyka, Nico
Hernández, Daniel
He, Yuan
Ding, Zifeng
Xiong, Bo
Zhou, Dongzhuoran
Kharlamov, Evgeny
Staab, Steffen
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2508_20131
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ArgRAG: Explainable Retrieval Augmented Generation using Quantitative Bipolar Argumentation
Zhu, Yuqicheng
Potyka, Nico
Hernández, Daniel
He, Yuan
Ding, Zifeng
Xiong, Bo
Zhou, Dongzhuoran
Kharlamov, Evgeny
Staab, Steffen
Artificial Intelligence
Machine Learning
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.
title ArgRAG: Explainable Retrieval Augmented Generation using Quantitative Bipolar Argumentation
topic Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2508.20131