# LLMGuard: Guarding Against Unsafe LLM Behavior

arXiv: https://arxiv.org/abs/2403.00826 · HTML: https://mlsanity.com/paper/2403.00826/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 17 references that are in the map.
- First posted on arXiv 27 Feb 2024.

## Builds on (most cited first, 7 of 7)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Ex Machina: Personal Attacks Seen at Scale](https://mlsanity.com/paper/1610.08914/) (2016)
- [AMMUS : A Survey of Transformer-based Pretrained Models in Natural Language Processing](https://mlsanity.com/paper/2108.05542/) (2021)
- [The MiniPile Challenge for Data-Efficient Language Models](https://mlsanity.com/paper/2304.08442/) (2023)
- [MathBERT: A Pre-Trained Model for Mathematical Formula Understanding](https://mlsanity.com/paper/2105.00377/) (2021)
- [Advancements in Scientific Controllable Text Generation Methods](https://mlsanity.com/paper/2307.05538/) (2023)

## Built on by (most cited first, 13 of 13)

- [A Survey on Privacy Risks and Protection in Large Language Models](https://mlsanity.com/paper/2505.01976/) (2025)
- [SoK: Evaluating Jailbreak Guardrails for Large Language Models](https://mlsanity.com/paper/2506.10597/) (2025)
- [Swiss Cheese Model for AI Safety: A Taxonomy and Reference Architecture for Multi-Layered Guardrails of Foundation Model Based Agents](https://mlsanity.com/paper/2408.02205/) (2024)
- [AgentTrace: A Structured Logging Framework for Agent System Observability](https://mlsanity.com/paper/2602.10133/) (2026)
- [LoRA-Guard: Parameter-Efficient Guardrail Adaptation for Content Moderation of Large Language Models](https://mlsanity.com/paper/2407.02987/) (2024)
- [Takedown: How It's Done in Modern Coding Agent Exploits](https://mlsanity.com/paper/2509.24240/) (2025)
- [ExpShield: Safeguarding Web Text from Unauthorized Crawling and LLM Exploitation](https://mlsanity.com/paper/2412.21123/) (2024)
- [Calibrated Predictive Lower Bounds on Time-to-Unsafe-Sampling in LLMs](https://mlsanity.com/paper/2506.13593/) (2025)
- [Playing Devil's Advocate: Unmasking Toxicity and Vulnerabilities in Large Vision-Language Models](https://mlsanity.com/paper/2501.09039/) (2025)
- [Building Understandable Messaging for Policy and Evidence Review (BUMPER) with AI](https://mlsanity.com/paper/2407.12812/) (2024)
- [Grade Guard: A Smart System for Short Answer Automated Grading](https://mlsanity.com/paper/2504.01253/) (2025)
- [When Harmful Content Gets Camouflaged: Unveiling Perception Failure of LVLMs with CamHarmTI](https://mlsanity.com/paper/2512.03087/) (2025)
- [Clouding the Mirror: Stealthy Prompt Injection Attacks Targeting LLM-based Phishing Detection](https://mlsanity.com/paper/2602.05484/) (2026)

## Abstract (arXiv)

Although the rise of Large Language Models (LLMs) in enterprise settings brings new opportunities and capabilities, it also brings challenges, such as the risk of generating inappropriate, biased, or misleading content that violates regulations and can have legal concerns. To alleviate this, we present "LLMGuard", a tool that monitors user interactions with an LLM application and flags content against specific behaviours or conversation topics. To do this robustly, LLMGuard employs an ensemble of detectors.