提出可解释RAG系统的新框架，无需修改模型即可分析检索与生成过程。
Towards End-to-End Model-Agnostic Explanations for RAG Systems
- 基于扰动技术构建通用后处理解释框架，不依赖具体模型。
- 设计多种评估策略验证解释有效性，证明方法在不同场景下可靠。
- 适合关注RAG系统可信度的研究者与工程师使用。
检索增强生成（RAG）系统虽因提升模型响应可靠性而广受欢迎，但其可信度与可解释性仍面临挑战。本文提出一种全新的、整体性的、模型无关的后处理解释框架，利用扰动技术解释RAG系统中的检索与生成过程。我们设计了多种评估策略来验证这些解释的有效性，并探讨了模型无关解释在RAG系统中的充分性。本工作旨在推动构建更可靠、可解释的RAG系统，促进该领域的协同研究。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。