This event is in the past.It took place on April 29, 2026 at West Hall.
Explore how statistics can make AI evaluation more rigorous. This dissertation defense presents three novel frameworks for testing large language models with scientific precision, from prompt sensitivity analysis to bridging human and automated judgments.
Academic talk
Dissertation defense
AI research
Statistics focus
Tips
đopen to the public, no registration needed
đ€covers cutting-edge LLM evaluation methods
Principled Evaluation of Large Language Models: A Statistical Perspective
Burns Park
Explore how statistics can make AI evaluation more rigorous. This dissertation defense presents three novel frameworks for testing large language models with scientific precision, from prompt sensitivity analysis to bridging human and automated judgments.
Academic talk
Dissertation defense
AI research
Statistics focus
Tips
đopen to the public, no registration needed
đ€covers cutting-edge LLM evaluation methods
Make it an outing
Add nearby spots before or after your event