# Granite Guardian

arXiv: https://arxiv.org/abs/2412.07724 · HTML: https://mlsanity.com/paper/2412.07724/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- Placed in Safety alignment, refusal and guardrails, one of 12 directions in LLM safety and security.
- First posted on arXiv 10 Dec 2024.

## Placed in

- LLM safety and security / [Safety alignment, refusal and guardrails](https://mlsanity.com/safety/safety-alignment-refusal-and-guardrails/)

## Built on by (most cited first, 25 of 25)

- [Unsafer in Many Turns: Benchmarking and Defending Multi-Turn Safety Risks in Tool-Using Agents](https://mlsanity.com/paper/2602.13379/) (2026)
- [Benign Samples Matter! Fine-tuning On Outlier Benign Samples Severely Breaks Safety](https://mlsanity.com/paper/2505.06843/) (2025)
- [Large Reasoning Models Learn Better Alignment from Flawed Thinking](https://mlsanity.com/paper/2510.00938/) (2025)
- [SafeTy Reasoning Elicitation Alignment for Multi-Turn Dialogues](https://mlsanity.com/paper/2506.00668/) (2025)
- [Disentangled Safety Adapters Enable Efficient Guardrails and Flexible Inference-Time Alignment](https://mlsanity.com/paper/2506.00166/) (2025)
- [DARWIN: Evolving Jailbreak Adversary and Guardrail for LLM Safety Evaluation and Protection](https://mlsanity.com/paper/2607.19829/) (2026)
- [Evaluating the Robustness of Large Language Model Safety Guardrails Against Adversarial Attacks](https://mlsanity.com/paper/2511.22047/) (2025)
- [AudioGuard: Toward Comprehensive Audio Safety Protection Across Diverse Threat Models](https://mlsanity.com/paper/2604.08867/) (2026)
- [HalluGuard: Evidence-Grounded Small Reasoning Models to Mitigate Hallucinations in Retrieval-Augmented Generation](https://mlsanity.com/paper/2510.00880/) (2025)
- [AprielGuard](https://mlsanity.com/paper/2512.20293/) (2025)
- [VerifiableFL: Verifiable Claims for Federated Learning using Exclaves](https://mlsanity.com/paper/2412.10537/) (2024)
- [Identifying Features Associated with Bias Against 93 Stigmatized Groups in Language Models and Guardrail Model Safety Mitigation](https://mlsanity.com/paper/2512.19238/) (2025)
- [TWGuard: A Case Study of LLM Safety Guardrails for Localized Linguistic Contexts](https://mlsanity.com/paper/2604.16542/) (2026)
- [Cognitive Firewall: A Proactive, Zero-Trust, Multi-Gate Framework for LLM Safety](https://mlsanity.com/paper/2607.01277/) (2026)
- [Dark LLMs: The Growing Threat of Unaligned AI Models](https://mlsanity.com/paper/2505.10066/) (2025)
- [Concealment of Intent: A Game-Theoretic Analysis](https://mlsanity.com/paper/2505.20841/) (2025)
- [Answering the Wrong Question: Reasoning Trace Inversion for Abstention in LLMs](https://mlsanity.com/paper/2604.02230/) (2026)
- [HyperSafe: Inference-Time Safety Recovery for Fine-Tuned Language Models](https://mlsanity.com/paper/2607.11475/) (2026)
- [CPInj: Uncovering Prompt Injection Risks in Textual Collaborative Prompt Optimization](https://mlsanity.com/paper/2607.18622/) (2026)
- [Semalith v1.4: A Calibrated 184M Safety Classifier Achieving State-of-the-Art Prompt-Injection Detection at 44x Fewer Parameters than Llama-Guard-3-8B](https://mlsanity.com/paper/2607.22545/) (2026)
- [Policy-as-logic for robust reasoning over rules](https://mlsanity.com/paper/2608.11905/) (2026)
- [Probing the Prefill: Detecting Code Vulnerabilities via Latent Activations](https://mlsanity.com/paper/2608.16970/) (2026)
- [Towards Mitigating Deceptive Safety Alignment in Large Reasoning Models](https://mlsanity.com/paper/2609.36254/) (2026)
- [Towards a Unified Misuse Monitoring Benchmark](https://mlsanity.com/paper/2610.07089/) (2026)
- [Safeguarding LLMs via Model-Agnostic Latent Safety Signals from Dark Knowledge](https://mlsanity.com/paper/2610.07532/) (2026)

## Abstract (arXiv)

We introduce the Granite Guardian models, a suite of safeguards designed to provide risk detection for prompts and responses, enabling safe and responsible use in combination with any large language model (LLM). These models offer comprehensive coverage across multiple risk dimensions, including social bias, profanity, violence, sexual content, unethical behavior, jailbreaking, and hallucination-related risks such as context relevance, groundedness, and answer relevance for retrieval-augmented generation (RAG). Trained on a unique dataset combining human annotations from diverse sources and synthetic data, Granite Guardian models address risks typically overlooked by traditional risk detection models, such as jailbreaks and RAG-specific issues. With AUC scores of 0.871 and 0.854 on harmful content and RAG-hallucination-related benchmarks respectively, Granite Guardian is the most generalizable and competitive model available in the space. Released as open-source, Granite Guardian aims to promote responsible AI development across the community. https://github.com/ibm-granite/granite-guardian