Published 'Literature Meets Data: A Synergistic Approach to Hypothesis Generation'; 'Hypothesis Generation with Large Language Models'; 'Machine Explanations and Human Understanding' which won the Best Paper Award at the ICML 2022 Workshop on Human-Machine Collaboration and Teaming; 'Learning Human-Compatible Representations for Case-Based Decision Support'; Co-organizes an online seminar on AI & Scientific Discovery.
Research Experience
Visiting scientist at Abridge; Focuses on how to build an effective communication protocol between humans and AI; Explores helping AI understand human goals and assist humans in specifying their goals; Develops complementary AI that accounts for human intuitions/biases; Works on making powerful AI interpretable.
Background
Associate Professor at the Department of Computer Science and Data Science at the University of Chicago; Directs the Chicago Human+AI lab (CHAI); Research interests lie in bringing together social sciences and machine learning to develop the best AI for humans. Applications include scientific discoveries, healthcare, and governance and democratic processes.
Miscellany
Blog post 'The Mirage of Autonomous AI Scientists'; Developed a communication game called HR Simulator™; Involved in PhD program admissions.