EthicsBench
AI Ethics and Regulation, Structured.
A neutral and open-access resource that curates leading ethical benchmarks and AI governance frameworks from around the world.
Benchmarks
View AllFHIBE
Fairness/VisionFair Human-centric Image Benchmark for Evaluation - A globally diverse dataset for evaluating fairne...
TrustLLM
Comprehensive SafetyA comprehensive framework for evaluating the trustworthiness of LLMs across six dimensions: truthful...
TruthfulQA
TruthfulnessA benchmark to measure whether a language model is truthful in generating answers to questions, spec...
BBQ (Bias Benchmark for QA)
Fairness/BiasA dataset of question sets designed to highlight social biases against people belonging to protected...
ETHICS Dataset
Moral JudgmentA benchmark for evaluating AI systems on their ability to make ethical judgments across multiple dom...
SCRUPLES
Moral DilemmasA corpus of ethical judgments over real-life anecdotes, designed to evaluate whether AI can predict ...
Regulations
View AllEU AI Act
EUThe first comprehensive legal framework for AI in the European Union, establishing a risk-based appr...
AI Guidelines for Business
JapanGuidelines from METI providing practical guidance for ethical and secure AI use in Japanese industry...
UK AI Safety Institute
UKGovernment institution focused on evaluating and testing the safety of advanced AI systems....
Executive Order on AI Safety
USPresidential executive order establishing new standards for AI safety and security, protecting priva...
Interim Measures for Generative AI
ChinaRegulations governing the development and deployment of generative AI services in China, with requir...
Blueprint for an AI Bill of Rights
USA White House framework outlining five principles to guide the design, use, and deployment of automa...