{"ID":2878127,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.20131","arxiv_id":"2508.20131","title":"ArgRAG: Explainable Retrieval Augmented Generation using Quantitative Bipolar Argumentation","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.","short_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 alter...","url_abs":"https://arxiv.org/abs/2508.20131","url_pdf":"https://arxiv.org/pdf/2508.20131v1","authors":"[\"Yuqicheng Zhu\",\"Nico Potyka\",\"Daniel Hernández\",\"Yuan He\",\"Zifeng Ding\",\"Bo Xiong\",\"Dongzhuoran Zhou\",\"Evgeny Kharlamov\",\"Steffen Staab\"]","published":"2025-08-26T13:54:51Z","proceeding":"cs.AI","tasks":"[\"cs.AI\",\"cs.LG\"]","methods":"[\"RAG\",\"Language Model\"]","has_code":false}