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

2025/02/08 by Bo Ni, Ni, Bo, Zheyuan Liu +36 · 1 voice · 13 citations
Computer Science · #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #Topic Modeling

paper · pdf · doi:10.48550/arxiv.2502.06872

openalex publication_date 2025/02/08 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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.

Cited by

• Learning to Code with Context: A Study-Based Approach
• Principled Context Engineering for RAG: Statistical Guarantees via Conformal Prediction
• RAG Makes Guardrails Unsafe? Investigating Robustness of Guardrails under RAG-style Contexts
• HalluGuard: Evidence-Grounded Small Reasoning Models to Mitigate Hallucinations in Retrieval-Augmented Generation
• Dual-Space Smoothness for Robust and Balanced LLM Unlearning
• Steering Multimodal Large Language Models Decoding for Context-Aware Safety
• Effective Damage Data Generation by Fusing Imagery with Human Knowledge Using Vision-Language Models
• Multi-Agent Retrieval-Augmented Framework for Evidence-Based Counterspeech Against Health Misinformation
• RAG Safety: Exploring Knowledge Poisoning Attacks to Retrieval-Augmented Generation
• MemOS: A Memory OS for AI System
• MrM: Black-Box Membership Inference Attacks against Multimodal RAG Systems
• Tools in the Loop: Quantifying Uncertainty of LLM Question Answering Systems That Use Tools
• Fine-grained Contrastive Learning for ECG-Report Alignment with Waveform Enhancement

Discussions

• There exist many techniques reduce hallucinations in enterprise RAG systems. See this survey: Towards Trustworthy Retrieval Augmented Generation for Large Language Models: A Survey . Aside from the te [stackexchange, 1 points]

Related

• Trustworthiness in Retrieval-Augmented Generation Systems: A Survey
• A Systematic Review of Key Retrieval-Augmented Generation (RAG) Systems: Progress, Gaps, and Future Directions
• Astute RAG: Overcoming Imperfect Retrieval Augmentation and Knowledge Conflicts for Large Language Models
• A Comprehensive Survey of Retrieval-Augmented Generation (RAG): Evolution, Current Landscape and Future Directions
• Deploying Large Language Models With Retrieval Augmented Generation