Pith. sign in

REVIEW 4 cited by

RAG LLMs are Not Safer: A Safety Analysis of Retrieval-Augmented Generation for Large Language Models

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2504.18041 v1 pith:J7N4DTFH submitted 2025-04-25 cs.CL cs.AI

classification cs.CLcs.AI
keywords safetyllmsmodelschangesafeanalysisfindgeneration
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original 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.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Risky Business: Measuring The Faithfulness-Safety Tension

    cs.AI 2026-08 conditional novelty 7.0 of 10

    Faithful reasoning and safety pull in opposite directions in current reasoning models, and the two behaviors are controlled by anti-correlated internal vectors that can be steered independently.

  2. Safety Degradation in AI Agents

    cs.CY 2025-05 conditional novelty 6.0 of 10

    Adding retrieval to aligned LLMs degrades safety: refusal rates fall, bias and harmfulness rise, and prompt-based mitigation only partially restores alignment.

  3. Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval

    cs.CR 2025-05 conditional novelty 5.0 of 10

    SCR uses retrieval-augmented generation to fetch refusal examples that block jailbreak attacks, but the reported advantages are partly overstated.

  4. Foundation Model Driven Robotics: A Comprehensive Review

    cs.RO 2025-07 conditional novelty 2.0 of 10

    A review of foundation-model-driven robotics that synthesizes recent work across perception, planning, control, HRI, simulation, and sim-to-real transfer, and highlights open challenges.

Pith tools