Holistic Evaluation of Language Models (HELM)

Percy Liang, Rishi Bommasani, Tony Lee, et al., Transactions on Machine Learning Research, 2022

Evaluates many language models across a broad set of scenarios and several metrics at once — including calibration, robustness, fairness, bias and toxicity — rather than accuracy alone.

BenchmarkIntermediateAbout 3 hours

OECD AI Principles

Organisation for Economic Co-operation and Development, OECD.AI, 2019

The first intergovernmental standard on AI, setting out values-based principles for trustworthy AI and recommendations to governments. The principles were updated in 2024.

Policy or legal textIntroductoryAbout 30 minutes