Stanford
University
  • Stanford Home
  • Maps & Directions
  • Search Stanford
  • Emergency Info
  • Terms of Use
  • Privacy
  • Copyright
  • Trademarks
  • Non-Discrimination
  • Accessibility
© Stanford University.  Stanford, California 94305.
Sanmi Koyejo | Beyond Benchmarks: Building a Science of AI Measurement | Stanford HAI
Skip to content
  • About

    • About
    • People
    • Get Involved with HAI
    • Support HAI
    • Subscribe to Email
  • Research

    • Research
    • Fellowship Programs
    • Grants
    • Student Affinity Groups
    • Centers & Labs
    • Research Publications
    • Research Partners
  • Education

    • Education
    • Executive and Professional Education
    • Government and Policymakers
    • K-12
    • Stanford Students
  • Policy

    • Policy
    • Policy Publications
    • Policymaker Education
    • Student Opportunities
  • AI Index

    • AI Index
    • AI Index Report
    • Global Vibrancy Tool
    • People
  • News
  • Events
  • Industry
  • Centers & Labs
Navigate
  • About
  • Events
  • AI Glossary
  • Careers
  • Search
Participate
  • Get Involved
  • Support HAI
  • Contact Us

Stay Up To Date

Get the latest news, advances in research, policy work, and education program updates from HAI in your inbox weekly.

Sign Up For Latest News

Your browser does not support the video tag.
eventSeminar

Sanmi Koyejo | Beyond Benchmarks: Building a Science of AI Measurement

Status
Past
Date
Wednesday, March 19, 2025 12:00 PM - 1:15 PM PST/PDT
Location
Gates Computer Science Building Room 119
Topics
Sciences (Social, Health, Biological, Physical)
Attend Virtually

The widepread deployment of AI systems in critical domains demands more rigorous approaches to evaluating their capabilities and safety.

Share
Link copied to clipboard!
Event Contact
Annie Benisch
abenisch@stanford.edu

Related Events

NVIDIA & Marlowe: Scaling Data Science Workloads with RAPIDS
WorkshopJul 15, 20262:00 PM - 3:30 PM
July
15
2026

This workshop will cover how NVIDIA RAPIDS offers a seamless experience to enable GPU-acceleration for many existing data science tasks with zero code changes. You will learn how to use GPU-accelerated tools to conduct data science faster, leading to more scalable, reliable, and cost-effective results!

Event

NVIDIA & Marlowe: Scaling Data Science Workloads with RAPIDS

Jul 15, 20262:00 PM - 3:30 PM

This workshop will cover how NVIDIA RAPIDS offers a seamless experience to enable GPU-acceleration for many existing data science tasks with zero code changes. You will learn how to use GPU-accelerated tools to conduct data science faster, leading to more scalable, reliable, and cost-effective results!

Empirical Methods in the Age of AI Conference
ConferenceOct 02, 2026
October
02
2026

Save the Date. Artificial intelligence is transforming how researchers collect, analyze, and learn from data. As AI systems become increasingly integrated into scientific discovery, business decision-making, and policy analysis, they are reshaping both the questions researchers can ask and the methods they use to answer them.

Event

Empirical Methods in the Age of AI Conference

Oct 02, 2026

Save the Date. Artificial intelligence is transforming how researchers collect, analyze, and learn from data. As AI systems become increasingly integrated into scientific discovery, business decision-making, and policy analysis, they are reshaping both the questions researchers can ask and the methods they use to answer them.

While current evaluation practices rely on static benchmarks, these methods face fundamental efficiency, reliability, and real-world relevance challenges. This talk presents a path toward a measurement framework that bridges established psychometric principles with modern AI evaluation needs. We demonstrate how techniques from Item Response Theory, amortized computation, and predictability analysis can substantially improve the rigor and efficiency of AI evaluation. Through case studies in safety assessment and capability measurement, we show how this approach can enable more reliable, scalable, and meaningful evaluation of AI systems. This work points toward a broader vision: evolving AI evaluation from a collection of benchmarks into a rigorous measurement science that can effectively guide research, deployment, and policy decisions.

Speaker
Sanmi Koyejo
Assistant Professor of Computer Science, Stanford University; Faculty Affiliate, Stanford HAI

Watch the Event Recording