RAG LLMs are Not Safer: A Safety Analysis of Retrieval-Augmented Generation for Large Language Models
Bang An, Shiyue Zhang, Mark Dredze
Abstract
Efforts to ensure the safety of large language models (LLMs) include safety fine-tuning, evaluation, and red teaming.However, despite the widespread use of the Retrieval-Augmented Generation (RAG) framework, AI safety work focuses on standard LLMs, which means we know little about how RAG use cases change a model’s safety profile. We conduct a detailed comparative analysis of RAG and non-RAG frameworks with eleven LLMs. We find that RAG can make models less safe and change their safety profile. We explore the causes of this change and find that even combinations of safe models with safe documents can cause unsafe generations. In addition, we evaluate some existing red teaming methods for RAG settings and show that they are less effective than when used for non-RAG settings. Our work highlights the need for safety research and red-teaming methods specifically tailored for RAG LLMs.
BibTeX
@inproceedings{an-etal-2025-rag,
title = "{RAG} {LLM}s are Not Safer: A Safety Analysis of Retrieval-Augmented Generation for Large Language Models",
author = "An, Bang and
Zhang, Shiyue and
Dredze, Mark",
editor = "Chiruzzo, Luis and
Ritter, Alan and
Wang, Lu",
booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
month = apr,
year = "2025",
address = "Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.naacl-long.281/",
pages = "5444--5474",
ISBN = "979-8-89176-189-6"
}