# Introducing v0.5 of the AI Safety Benchmark from MLCommons

arXiv: https://arxiv.org/abs/2404.12241 · HTML: https://mlsanity.com/paper/2404.12241/

## Key facts

- Cited by 62 papers in the map (data through 14 Oct 2026).
- Builds on 73 of its 180 references that are in the map.
- First posted on arXiv 18 Apr 2024.

## Builds on (most cited first, 30 of 73)

- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [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)
- [Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models](https://mlsanity.com/paper/2206.04615/) (2022)
- [Jailbroken: How Does LLM Safety Training Fail?](https://mlsanity.com/paper/2307.02483/) (2023)
- [Concrete Problems in AI Safety](https://mlsanity.com/paper/1606.06565/) (2016)
- [HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal](https://mlsanity.com/paper/2402.04249/) (2024)
- [RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models](https://mlsanity.com/paper/2009.11462/) (2020)
- [Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations](https://mlsanity.com/paper/2312.06674/) (2023)
- [PaLM 2 Technical Report](https://mlsanity.com/paper/2305.10403/) (2023)
- [Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!](https://mlsanity.com/paper/2310.03693/) (2023)
- [Large Language Models are not Fair Evaluators](https://mlsanity.com/paper/2305.17926/) (2023)
- [Towards Understanding Sycophancy in Language Models](https://mlsanity.com/paper/2310.13548/) (2023)
- [BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Dataset](https://mlsanity.com/paper/2307.04657/) (2023)
- [Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned](https://mlsanity.com/paper/2209.07858/) (2022)
- [BBQ: A Hand-Built Bias Benchmark for Question Answering](https://mlsanity.com/paper/2110.08193/) (2021)
- [The Woman Worked as a Babysitter: On Biases in Language Generation](https://mlsanity.com/paper/1909.01326/) (2019)
- [Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training](https://mlsanity.com/paper/2401.05566/) (2024)
- [DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models](https://mlsanity.com/paper/2306.11698/) (2023)
- [Release Strategies and the Social Impacts of Language Models](https://mlsanity.com/paper/1908.09203/) (2019)
- [Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks](https://mlsanity.com/paper/2404.02151/) (2024)
- [Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment](https://mlsanity.com/paper/2308.05374/) (2023)
- [Safety-Tuned LLaMAs: Lessons From Improving the Safety of Large Language Models that Follow Instructions](https://mlsanity.com/paper/2309.07875/) (2023)
- [A StrongREJECT for Empty Jailbreaks](https://mlsanity.com/paper/2402.10260/) (2024)
- [TrustLLM: Trustworthiness in Large Language Models](https://mlsanity.com/paper/2401.05561/) (2024)
- [On Evaluating Adversarial Robustness of Large Vision-Language Models](https://mlsanity.com/paper/2305.16934/) (2023)
- [FinanceBench: A New Benchmark for Financial Question Answering](https://mlsanity.com/paper/2311.11944/) (2023)

## Built on by (most cited first, 30 of 62)

- [SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal](https://mlsanity.com/paper/2406.14598/) (2024)
- [ST-WebAgentBench: A Benchmark for Evaluating Safety and Trustworthiness in Web Agents](https://mlsanity.com/paper/2410.06703/) (2024)
- [Aegis2.0: A Diverse AI Safety Dataset and Risks Taxonomy for Alignment of LLM Guardrails](https://mlsanity.com/paper/2501.09004/) (2025)
- [Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations](https://mlsanity.com/paper/2411.10414/) (2024)
- [AI Agents Under Threat: A Survey of Key Security Challenges and Future Pathways](https://mlsanity.com/paper/2406.02630/) (2024)
- [Establishing Best Practices for Building Rigorous Agentic Benchmarks](https://mlsanity.com/paper/2507.02825/) (2025)
- [Safetywashing: Do AI Safety Benchmarks Actually Measure Safety Progress?](https://mlsanity.com/paper/2407.21792/) (2024)
- [The Perfect Blend: Redefining RLHF with Mixture of Judges](https://mlsanity.com/paper/2409.20370/) (2024)
- [Safety Pretraining: Toward the Next Generation of Safe AI](https://mlsanity.com/paper/2504.16980/) (2025)
- [Can Knowledge Editing Really Correct Hallucinations?](https://mlsanity.com/paper/2410.16251/) (2024)
- [Video-SafetyBench: A Benchmark for Safety Evaluation of Video LVLMs](https://mlsanity.com/paper/2505.11842/) (2025)
- [Exploring Safety-Utility Trade-Offs in Personalized Language Models](https://mlsanity.com/paper/2406.11107/) (2024)
- [AdvPrefix: An Objective for Nuanced LLM Jailbreaks](https://mlsanity.com/paper/2412.10321/) (2024)
- [Know Thy Judge: On the Robustness Meta-Evaluation of LLM Safety Judges](https://mlsanity.com/paper/2503.04474/) (2025)
- [RAG LLMs are Not Safer: A Safety Analysis of Retrieval-Augmented Generation for Large Language Models](https://mlsanity.com/paper/2504.18041/) (2025)
- [Can Editing LLMs Inject Harm?](https://mlsanity.com/paper/2407.20224/) (2024)
- [BingoGuard: LLM Content Moderation Tools with Risk Levels](https://mlsanity.com/paper/2503.06550/) (2025)
- [Eureka: Evaluating and Understanding Large Foundation Models](https://mlsanity.com/paper/2409.10566/) (2024)
- [WalledEval: A Comprehensive Safety Evaluation Toolkit for Large Language Models](https://mlsanity.com/paper/2408.03837/) (2024)
- [ClawSafety: "Safe" LLMs, Unsafe Agents](https://mlsanity.com/paper/2604.01438/) (2026)
- [Adversarial Poetry as a Universal Single-Turn Jailbreak Mechanism in Large Language Models](https://mlsanity.com/paper/2511.15304/) (2025)
- [Risks and Opportunities of Open-Source Generative AI](https://mlsanity.com/paper/2405.08597/) (2024)
- [MSTS: A Multimodal Safety Test Suite for Vision-Language Models](https://mlsanity.com/paper/2501.10057/) (2025)
- [Automated Benchmark Auditing for AI Agents and Large Language Models](https://mlsanity.com/paper/2605.26079/) (2026)
- [Evaluation-Driven Development and Operations of LLM Agents: A Process Model and Reference Architecture](https://mlsanity.com/paper/2411.13768/) (2024)
- [Building Safe GenAI Applications: An End-to-End Overview of Red Teaming for Large Language Models](https://mlsanity.com/paper/2503.01742/) (2025)
- [SafetyAnalyst: Interpretable, Transparent, and Steerable Safety Moderation for AI Behavior](https://mlsanity.com/paper/2410.16665/) (2024)
- [VLDBench Evaluating Multimodal Disinformation with Regulatory Alignment](https://mlsanity.com/paper/2502.11361/) (2025)
- [HoliSafe: Holistic Safety Benchmarking and Modeling for Vision-Language Model](https://mlsanity.com/paper/2506.04704/) (2025)
- [RealHarm: A Collection of Real-World Language Model Application Failures](https://mlsanity.com/paper/2504.10277/) (2025)

## Abstract (arXiv)

This paper introduces v0.5 of the AI Safety Benchmark, which has been created by the MLCommons AI Safety Working Group. The AI Safety Benchmark has been designed to assess the safety risks of AI systems that use chat-tuned language models. We introduce a principled approach to specifying and constructing the benchmark, which for v0.5 covers only a single use case (an adult chatting to a general-purpose assistant in English), and a limited set of personas (i.e., typical users, malicious users, and vulnerable users). We created a new taxonomy of 13 hazard categories, of which 7 have tests in the v0.5 benchmark. We plan to release version 1.0 of the AI Safety Benchmark by the end of 2024. The v1.0 benchmark will provide meaningful insights into the safety of AI systems. However, the v0.5 benchmark should not be used to assess the safety of AI systems. We have sought to fully document the limitations, flaws, and challenges of v0.5. This release of v0.5 of the AI Safety Benchmark includes (1) a principled approach to specifying and constructing the benchmark, which comprises use cases, types of systems under test (SUTs), language and context, personas, tests, and test items; (2) a taxonomy of 13 hazard categories with definitions and subcategories; (3) tests for seven of the hazard categories, each comprising a unique set of test items, i.e., prompts. There are 43,090 test items in total, which we created with templates; (4) a grading system for AI systems against the benchmark; (5) an openly available platform, and downloadable tool, called ModelBench that can be used to evaluate the safety of AI systems on the benchmark; (6) an example evaluation report which benchmarks the performance of over a dozen openly available chat-tuned language models; (7) a test specification for the benchmark.