# Aegis2.0: A Diverse AI Safety Dataset and Risks Taxonomy for Alignment of LLM Guardrails

arXiv: https://arxiv.org/abs/2501.09004 · HTML: https://mlsanity.com/paper/2501.09004/

## Key facts

- Cited by 132 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.
- Builds on 25 of its 33 references that are in the map.
- First posted on arXiv 15 Jan 2025.

## Placed in

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

## Builds on (most cited first, 25 of 25)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [Gemma 2: Improving Open Language Models at a Practical Size](https://mlsanity.com/paper/2408.00118/) (2024)
- [HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal](https://mlsanity.com/paper/2402.04249/) (2024)
- [Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations](https://mlsanity.com/paper/2312.06674/) (2023)
- [BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Dataset](https://mlsanity.com/paper/2307.04657/) (2023)
- [BERTopic: Neural topic modeling with a class-based TF-IDF procedure](https://mlsanity.com/paper/2203.05794/) (2022)
- [Safe Latent Diffusion: Mitigating Inappropriate Degeneration in Diffusion Models](https://mlsanity.com/paper/2211.05105/) (2022)
- [WildGuard: Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs](https://mlsanity.com/paper/2406.18495/) (2024)
- [Safety-Tuned LLaMAs: Lessons From Improving the Safety of Large Language Models that Follow Instructions](https://mlsanity.com/paper/2309.07875/) (2023)
- [NeMo Guardrails: A Toolkit for Controllable and Safe LLM Applications with Programmable Rails](https://mlsanity.com/paper/2310.10501/) (2023)
- [A Holistic Approach to Undesired Content Detection in the Real World](https://mlsanity.com/paper/2208.03274/) (2022)
- [ToxicChat: Unveiling Hidden Challenges of Toxicity Detection in Real-World User-AI Conversation](https://mlsanity.com/paper/2310.17389/) (2023)
- [Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment](https://mlsanity.com/paper/2308.09662/) (2023)
- [MMA-Diffusion: MultiModal Attack on Diffusion Models](https://mlsanity.com/paper/2311.17516/) (2023)
- [A New Generation of Perspective API: Efficient Multilingual Character-level Transformers](https://mlsanity.com/paper/2202.11176/) (2022)
- [Do-Not-Answer: A Dataset for Evaluating Safeguards in LLMs](https://mlsanity.com/paper/2308.13387/) (2023)
- [AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts](https://mlsanity.com/paper/2404.05993/) (2024)
- [The Art of Defending: A Systematic Evaluation and Analysis of LLM Defense Strategies on Safety and Over-Defensiveness](https://mlsanity.com/paper/2401.00287/) (2023)
- [Introducing v0.5 of the AI Safety Benchmark from MLCommons](https://mlsanity.com/paper/2404.12241/) (2024)
- [AART: AI-Assisted Red-Teaming with Diverse Data Generation for New LLM-powered Applications](https://mlsanity.com/paper/2311.08592/) (2023)
- [CantTalkAboutThis: Aligning Language Models to Stay on Topic in Dialogues](https://mlsanity.com/paper/2404.03820/) (2024)
- [BiasX: "Thinking Slow" in Toxic Content Moderation with Explanations of Implied Social Biases](https://mlsanity.com/paper/2305.13589/) (2023)

## Built on by (most cited first, 30 of 132)

- [Qwen3Guard Technical Report](https://mlsanity.com/paper/2510.14276/) (2025)
- [NVIDIA Nemotron Nano 2: An Accurate and Efficient Hybrid Mamba-Transformer Reasoning Model](https://mlsanity.com/paper/2508.14444/) (2025)
- [Nemotron 3 Nano: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning](https://mlsanity.com/paper/2512.20848/) (2025)
- [GuardReasoner: Towards Reasoning-based LLM Safeguards](https://mlsanity.com/paper/2501.18492/) (2025)
- [Nemotron-H: A Family of Accurate and Efficient Hybrid Mamba-Transformer Models](https://mlsanity.com/paper/2504.03624/) (2025)
- [Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety](https://mlsanity.com/paper/2502.05206/) (2025)
- [Safety in Large Reasoning Models: A Survey](https://mlsanity.com/paper/2504.17704/) (2025)
- [PolyGuard: A Multilingual Safety Moderation Tool for 17 Languages](https://mlsanity.com/paper/2504.04377/) (2025)
- [Meta Context Engineering via Agentic Skill Evolution](https://mlsanity.com/paper/2601.21557/) (2026)
- [GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning](https://mlsanity.com/paper/2505.11049/) (2025)
- [Neither Valid nor Reliable? Investigating the Use of LLMs as Judges](https://mlsanity.com/paper/2508.18076/) (2025)
- [CultureGuard: Towards Culturally-Aware Dataset and Guard Model for Multilingual Safety Applications](https://mlsanity.com/paper/2508.01710/) (2025)
- [Reasoning as an Adaptive Defense for Safety](https://mlsanity.com/paper/2507.00971/) (2025)
- [SoK: Evaluating Jailbreak Guardrails for Large Language Models](https://mlsanity.com/paper/2506.10597/) (2025)
- [DynaGuard: A Dynamic Guardian Model With User-Defined Policies](https://mlsanity.com/paper/2509.02563/) (2025)
- [False Sense of Security: Why Probing-based Malicious Input Detection Fails to Generalize](https://mlsanity.com/paper/2509.03888/) (2025)
- [SAFEx: Analyzing Vulnerabilities of MoE-Based LLMs via Stable Safety-critical Expert Identification](https://mlsanity.com/paper/2506.17368/) (2025)
- [Rethinking Jailbreak Detection of Large Vision Language Models with Representational Contrastive Scoring](https://mlsanity.com/paper/2512.12069/) (2025)
- [LLM Safety From Within: Detecting Harmful Content with Internal Representations](https://mlsanity.com/paper/2604.18519/) (2026)
- [MrGuard: A Multilingual Reasoning Guardrail for Universal LLM Safety](https://mlsanity.com/paper/2504.15241/) (2025)
- [ReasoningShield: Safety Detection over Reasoning Traces of Large Reasoning Models](https://mlsanity.com/paper/2505.17244/) (2025)
- [Kelp: A Streaming Safeguard for Large Models via Latent Dynamics-Guided Risk Detection](https://mlsanity.com/paper/2510.09694/) (2025)
- [Sparse Models, Sparse Safety: Unsafe Routes in Mixture-of-Experts LLMs](https://mlsanity.com/paper/2602.08621/) (2026)
- [VLSU: Mapping the Limits of Joint Multimodal Understanding for AI Safety](https://mlsanity.com/paper/2510.18214/) (2025)
- [Lost in the Noise: How Reasoning Models Fail with Contextual Distractors](https://mlsanity.com/paper/2601.07226/) (2026)
- [ShieldVLM: Safeguarding the Multimodal Implicit Toxicity via Deliberative Reasoning with LVLMs](https://mlsanity.com/paper/2505.14035/) (2025)
- [OMNIGUARD: An Efficient Approach for AI Safety Moderation Across Languages and Modalities](https://mlsanity.com/paper/2505.23856/) (2025)
- [RedDebate: Safer Responses Through Multi-Agent Red Teaming Debates](https://mlsanity.com/paper/2506.11083/) (2025)
- [LionGuard 2: Building Lightweight, Data-Efficient & Localised Multilingual Content Moderators](https://mlsanity.com/paper/2507.15339/) (2025)
- [Efficient Switchable Safety Control in LLMs via Magic-Token-Guided Co-Training](https://mlsanity.com/paper/2508.14904/) (2025)

## Abstract (arXiv)

As Large Language Models (LLMs) and generative AI become increasingly widespread, concerns about content safety have grown in parallel. Currently, there is a clear lack of high-quality, human-annotated datasets that address the full spectrum of LLM-related safety risks and are usable for commercial applications. To bridge this gap, we propose a comprehensive and adaptable taxonomy for categorizing safety risks, structured into 12 top-level hazard categories with an extension to 9 fine-grained subcategories. This taxonomy is designed to meet the diverse requirements of downstream users, offering more granular and flexible tools for managing various risk types. Using a hybrid data generation pipeline that combines human annotations with a multi-LLM "jury" system to assess the safety of responses, we obtain Aegis 2.0, a carefully curated collection of 34,248 samples of human-LLM interactions, annotated according to our proposed taxonomy. To validate its effectiveness, we demonstrate that several lightweight models, trained using parameter-efficient techniques on Aegis 2.0, achieve performance competitive with leading safety models fully fine-tuned on much larger, non-commercial datasets. In addition, we introduce a novel training blend that combines safety with topic following data.This approach enhances the adaptability of guard models, enabling them to generalize to new risk categories defined during inference. We plan to open-source Aegis 2.0 data and models to the research community to aid in the safety guardrailing of LLMs.