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

Retrieval-Augmented Generation (RAG) enhances AI-generated content by integrating external knowledge, improving relevance, and reducing hallucinations. However, RAG also introduces risks related to reliability, safety, privacy, fairness, explainability, and accountability, which impact trustworthiness. While various methods aim to address these concerns, a unified framework is lacking. This survey bridges that gap by presenting a comprehensive roadmap for trustworthy RAG systems. We provide a structured analysis of key challenges, existing solutions, and future directions across these aspects. We further organize the field around how the retrieval and generation stages and the six trustworthiness dimensions interact, demonstrating their synergies and trade-offs through a controlled cross-dimensional analysis. Additionally, we highlight downstream applications where trustworthy RAG can make a significant impact, encouraging further research and adoption in real-world AI systems.

Authors

Institutions

Publication Details

Journal
ACM Computing Surveys
Published
2026-08-06
DOI
https://doi.org/10.1145/3837074
Citations
8
Primary Topic
Topic Modeling
Type
article
Field-Weighted Citation Impact
34.82
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

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

Krishnaram Kenthapadi, Leyao Wang, Luna Dong, Ryan A. Rossi et al.
8 citations
ACM Computing Surveys
Topic Modeling
34.82
article

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

Krishnaram Kenthapadi, Leyao Wang, Luna Dong, Ryan A. Rossi, Erik Blasch, Franck Dernoncourt, Xueqi Cheng, Tyler Derr, Md Mehrab Tanjim, Bo Ni, Wenqi Fan, Yinglong Xia, Nesreen K. Ahmed, Yuying Zhao, Zheyuan Liu, Xiaorui Liu, Meng Jiang, Yongjia Lei, Qingkai Zeng, Yu Wang
article en
8 citations

Abstract

Retrieval-Augmented Generation (RAG) enhances AI-generated content by integrating external knowledge, improving relevance, and reducing hallucinations. However, RAG also introduces risks related to reliability, safety, privacy, fairness, explainability, and accountability, which impact trustworthiness. While various methods aim to address these concerns, a unified framework is lacking. This survey bridges that gap by presenting a comprehensive roadmap for trustworthy RAG systems. We provide a structured analysis of key challenges, existing solutions, and future directions across these aspects. We further organize the field around how the retrieval and generation stages and the six trustworthiness dimensions interact, demonstrating their synergies and trade-offs through a controlled cross-dimensional analysis. Additionally, we highlight downstream applications where trustworthy RAG can make a significant impact, encouraging further research and adoption in real-world AI systems.

ACM Computing Surveys
Florida State University (US), University of Notre Dame (US), United States Air Force Research Laboratory (US), Adobe Systems (United States) (US), Oracle (United States) (US), Hong Kong Polytechnic University (HK), Vanderbilt University (US), Yale University (US), Florida Department of State (US), META Health (US)
Openalex Percentile: Top 1%
Topic Modeling
34.82
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.