Towards End-to-End Model-Agnostic Explanations for RAG Systems
On the map: Retrieval-augmented generation → RAG pipeline design and evaluation
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RAG pipeline design and evaluation, one of 15 directions in Retrieval-augmented generation. Builds on 4 of its 6 references that are in the map. First posted on arXiv 9 Sep 2025.
Builds on
4 of 6 references.
Closest ancestors · 2
Same direction, newest first
- 2024A Comprehensive Survey of Retrieval-Augmented Generation (RAG): Evolution, Current Landscape and Future Directions3 Oct
- 2023Retrieval-Augmented Generation for Large Language Models: A Survey18 Dec
Other references · 2
- 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
- 2024Trustworthiness in Retrieval-Augmented Generation Systems: A Surveycited by 83
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026Mapping the RAG Landscape: A Four Axis Taxonomy of Efficiency, Defense, Interactivity, and Reasoning
- 2025RAGVUE: A Diagnostic View for Explainable and Automated Evaluation of Retrieval-Augmented Generation
- 2024The Power of Noise: Redefining Retrieval for RAG Systems
- 2025RAGTrace: Understanding and Refining Retrieval-Generation Dynamics in Retrieval-Augmented Generation
- 2025Synergizing RAG and Reasoning: A Systematic Review
- 2024Eliciting Critical Reasoning in Retrieval-Augmented Language Models via Contrastive Explanations
- 2024Semantic Tokens in Retrieval Augmented Generation
- 2024Towards Understanding Systems Trade-offs in Retrieval-Augmented Generation Model Inference