Towards Trustworthy Retrieval Augmented Generation for Large Language Models: A Survey

TL;DR

This survey articulates a unified framework for trustworthy Retrieval-Augmented Generation (RAG) in large language models by dissecting six dimensions: reliability, privacy, safety, fairness, explainability, and accountability. It surveys the current methods, taxonomies, evaluation protocols, and datasets across the RAG pipeline (retrieval, augmentation, generation), and provides domain-specific discussions for healthcare, law, and education. The work highlights gaps in standardized benchmarks, the need for integrated uncertainty-robustness evaluation, and cross-cutting defenses against adversarial and privacy threats, proposing concrete future directions such as unified watermarking and knowledge-graph integration. By offering a structured taxonomy and actionable research directions, it aims to accelerate development of trustworthy, high-stakes RAG systems with rigorous governance and measurable trustworthiness. The practical impact lies in guiding researchers and practitioners to design RAG systems that are reliable, privacy-preserving, safe, fair, explainable, and auditable in real-world applications.

Abstract

Retrieval-Augmented Generation (RAG) is an advanced technique designed to address the challenges of Artificial Intelligence-Generated Content (AIGC). By integrating context retrieval into content generation, RAG provides reliable and up-to-date external knowledge, reduces hallucinations, and ensures relevant context across a wide range of tasks. However, despite RAG's success and potential, recent studies have shown that the RAG paradigm also introduces new risks, including robustness issues, privacy concerns, adversarial attacks, and accountability issues. Addressing these risks is critical for future applications of RAG systems, as they directly impact their trustworthiness. Although various methods have been developed to improve the trustworthiness of RAG methods, there is a lack of a unified perspective and framework for research in this topic. Thus, in this paper, we aim to address this gap by providing a comprehensive roadmap for developing trustworthy RAG systems. We place our discussion around five key perspectives: reliability, privacy, safety, fairness, explainability, and accountability. For each perspective, we present a general framework and taxonomy, offering a structured approach to understanding the current challenges, evaluating existing solutions, and identifying promising future research directions. To encourage broader adoption and innovation, we also highlight the downstream applications where trustworthy RAG systems have a significant impact.

Figures (1)

• Figure 1: An overview of the key components and dimensions of Trustworthy Retrieval Augmented Generation (RAG) for Large Language Models (LLMs) that are covered in this survey.