TRAILS Trustworthy Machine Learning Seminar Series

Speaker: Kaiqing Zhang, an assistant professor of electrical and computer engineering at the University of Maryland

Where: University of Maryland, CSIC 2120 and on Zoom: https://umd.zoom.us/j/93960331973?pwd=tVQ7gtFucJEkSYna38zePzkPpHm3J7.1

Talk: Towards Understanding and Post-training LLMs as Decision-Making Agents: A Regret-based Approach

[1] Do LLM Agents Have Regret? A Case Study in Online Learning and Games

[2] Post-Training LLMs as Better Decision-Making Agents: A Regret-Minimization Approach

Bio: Kaiqing Zhang is an assistant professor of electrical and computer engineering at the University of Maryland with an affiliate appointment in the University of Maryland Institute for Advanced Computer Studies.

About the TRAILS Trustworthy Machine Learning Seminar Series: Each week a researcher from across the TRAILS community presents current work on what it takes to make AI systems worth trusting: measuring and evaluating their behavior, interpreting and steering them, keeping them robust and secure, protecting privacy, and understanding how people actually rely on them — with occasional excursions into the philosophy and psychology of trust. Talks are 40 minutes, followed by 20 minutes of discussion.