Talk Title:Human-Model Interaction in Civic Sectors

Speaker: Fumeng Yang, Assistant Professor, Department of Computer Science, University of Maryland, College Park

Location: HBK 2105 and Zoom

Abstract:
Computational models—from probabilistic forecasts to AI foundation models—are increasingly shaping decisions in public life. It is critical to ensure that individuals and groups, from the general public to domain experts and data scientists, can perceive, use, and develop these models effectively and responsibly. In this talk, I will share my work on human-model interaction in three areas: election forecasting, AI for education, and AI for decision-making. I will first present our experiments using uncertainty visualizations to build appropriate trust in probabilistic election forecasts. I will then discuss our ongoing work on understanding K–12 teachers’ needs and co-designing an LLM-based classroom assessment authoring tool with them. Finally, if time permits, I will briefly introduce our survey of human-AI decision-making.

Bio:
Fumeng Yang is an Assistant Professor in the Department of Computer Science at the University of Maryland, College Park. Her research focuses on Human-Computer Interaction and Data Visualization, with an emphasis on how people interact with computational models in decision-making, education, and public communication. Her work has been published in premier venues such as CHI and VIS, and has been recognized with two Best Paper Awards and three Best Paper Honorable Mention Awards. Prior to joining UMD, she was a CCC/CRA Computing Innovation Postdoctoral Fellow at Northwestern University. She received her Ph.D. in Computer Science from Brown University.