# RAR: Setting Knowledge Tripwires for Retrieval Augmented Rejection

arXiv: https://arxiv.org/abs/2505.13581 · HTML: https://mlsanity.com/paper/2505.13581/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Privacy and security of RAG, one of 15 directions in Retrieval-augmented generation.
- Builds on 11 of its 11 references that are in the map.
- First posted on arXiv 19 May 2025.

## Placed in

- Retrieval-augmented generation / [Privacy and security of RAG](https://mlsanity.com/rag/privacy-and-security-of-rag/)

## Builds on (most cited first, 11 of 11)

- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations](https://mlsanity.com/paper/2312.06674/) (2023)
- [WildGuard: Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs](https://mlsanity.com/paper/2406.18495/) (2024)
- [OR-Bench: An Over-Refusal Benchmark for Large Language Models](https://mlsanity.com/paper/2405.20947/) (2024)
- [Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment](https://mlsanity.com/paper/2308.09662/) (2023)
- [AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts](https://mlsanity.com/paper/2404.05993/) (2024)
- [Machine Against the RAG: Jamming Retrieval-Augmented Generation with Blocker Documents](https://mlsanity.com/paper/2406.05870/) (2024)
- [SafeRAG: Benchmarking Security in Retrieval-Augmented Generation of Large Language Model](https://mlsanity.com/paper/2501.18636/) (2025)
- [RAG LLMs are Not Safer: A Safety Analysis of Retrieval-Augmented Generation for Large Language Models](https://mlsanity.com/paper/2504.18041/) (2025)
- [Class-RAG: Real-Time Content Moderation with Retrieval Augmented Generation](https://mlsanity.com/paper/2410.14881/) (2024)

## Built on by (most cited first, 3 of 3)

- [Adversarial Distilled Retrieval-Augmented Guarding Model for Online Malicious Intent Detection](https://mlsanity.com/paper/2509.14622/) (2025)
- [Relevance as a Vulnerability: How Web Retrieval Degrades Safety Alignment in LLM Agents](https://mlsanity.com/paper/2605.29224/) (2026)
- [PolicyMem: Geometric Policy Memory for LLM Governance](https://mlsanity.com/paper/2609.13734/) (2026)

## Abstract (arXiv)

Content moderation for large language models (LLMs) remains a significant challenge, requiring flexible and adaptable solutions that can quickly respond to emerging threats. This paper introduces Retrieval Augmented Rejection (RAR), a novel approach that leverages a retrieval-augmented generation (RAG) architecture to dynamically reject unsafe user queries without model retraining. By strategically inserting and marking malicious documents into the vector database, the system can identify and reject harmful requests when these documents are retrieved. Our preliminary results show that RAR achieves comparable performance to embedded moderation in LLMs like Claude 3.5 Sonnet, while offering superior flexibility and real-time customization capabilities, a fundamental feature to timely address critical vulnerabilities. This approach introduces no architectural changes to existing RAG systems, requiring only the addition of specially crafted documents and a simple rejection mechanism based on retrieval results.