{"ID":2873001,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.07620","arxiv_id":"2509.07620","title":"Towards End-to-End Model-Agnostic Explanations for RAG Systems","abstract":"Retrieval Augmented Generation (RAG) systems, despite their growing popularity for enhancing model response reliability, often struggle with trustworthiness and explainability. In this work, we present a novel, holistic, model-agnostic, post-hoc explanation framework leveraging perturbation-based techniques to explain the retrieval and generation processes in a RAG system. We propose different strategies to evaluate these explanations and discuss the sufficiency of model-agnostic explanations in RAG systems. With this work, we further aim to catalyze a collaborative effort to build reliable and explainable RAG systems.","short_abstract":"Retrieval Augmented Generation (RAG) systems, despite their growing popularity for enhancing model response reliability, often struggle with trustworthiness and explainability. In this work, we present a novel, holistic, model-agnostic, post-hoc explanation framework leveraging perturbation-based techniques to explain...","url_abs":"https://arxiv.org/abs/2509.07620","url_pdf":"https://arxiv.org/pdf/2509.07620v1","authors":"[\"Viju Sudhi\",\"Sinchana Ramakanth Bhat\",\"Max Rudat\",\"Roman Teucher\",\"Nicolas Flores-Herr\"]","published":"2025-09-09T11:47:40Z","proceeding":"cs.IR","tasks":"[\"cs.IR\"]","methods":"[]","has_code":false}