Percy Liang — Stanford HAI, HELM

**Percy Liang** is an associate professor of Computer Science at **Stanford University** and a faculty affiliate at the **Stanford Human-Centered AI Institute (HAI)**. He is the creator of **HELM (Holistic Evaluation of Language Models)**, the most comprehensive benchmark for evaluating large language models across multiple dimensions — accuracy, fairness, robustness, calibration, and efficiency. His research focuses on making AI evaluation rigorous, transparent, and reproducible.\n\nPercy's perspective is that the AI industry suffers from a measurement problem — companies cherry-pick benchmarks, inflate capabilities, and lack transparency about model limitations. HELM was created to provide an independent, comprehensive evaluation that holds all models to the same standard.