报告地点：行健楼学术活动室526
邀请人：杜秀丽教授
摘要：In this talk, I will discuss recent work on evaluating the sports understanding of LLMs, using newly introduced benchmark datasets. Our evaluation covers a range of tasks, from basic queries about rules and historical facts to complex, context-specific reasoning, as well as assessing the sports reasoning capabilities of video language models. Experiments show that models fall short on hard tasks that require deep reasoning and rule-based understanding. We hope the published benchmarks will serve as a critical step toward improving models’ capabilities in sports understanding and reasoning.
Intro: Weining Shen is Associate Professor of Statistics at University of California, Irvine. He received his PhD from North Carolina State University and a bachelor’s degree from University of Science and Technology of China. He is an associate editor for a few statistical journals including JASA, AoAS, and Statistica Sinica. Prof. Shen’s research interest includes Bayesian methods, machine learning, high-dimensional models, and applications in neuroscience, biology, sports analytics, and education assessment.
