Harman Kaur is a PhD candidate in both the department of Computer Science and the School of Information at the University of Michigan, where she is advised by Eric Gilbert and Cliff Lampe. Her research interests lie in human-AI collaboration and interpretable ML. Specifically, she studies interpretability tools from a human-centered perspective and designs solutions to support the bounded nature of human rationality in the context of ML-based systems. She has published several papers at top-tier human-computer interaction venues, such as CHI, CSCW, IUI, and UIST. Her work has won Best Paper Honorable Mention awards at CHI and IUI. She has also completed several internships at Microsoft Research and the Allen Institute for AI. Prior to Michigan, Harman received a BS in Computer Science from the University of Minnesota.
Leveraging Human Cognition for AI Interaction
Fields of interest
BS in Computer Science, University of Minnesota, 2016
MS in Computer Science and Engineering, University of Michigan, 2019
H. Kaur, E. Adar, E. Gilbert, and C. Lampe. Sensible AI: Re-imagining Interpretability and Explainability using Sensemaking Theory. In Proceedings of the ACM Conference on Fairness, Accountability, and Transparency (FAccT 2022).
H. Kaur, H. Nori, S. Jenkins, R. Caruana, H. Wallach, and J.W. Vaughan. Interpreting Interpretability: Understanding Data Scientists’ Use of Interpretability Tools for Machine Learning. In Proceedings of the ACM Conference on Human Factors in Computing Systems (CHI 2020).
D.A. Melis, H. Kaur, H. Daumé, H. Wallach, and J.W. Vaughan. A Human-Centered Approach to Interpretability Using Weight of Evidence. In Proceedings of the AAAI Conference on Human Computation and Crowdsourcing (HCOMP 2021)
H. Kaur, A.C. Williams, D. McDuff, M. Czerwinski, J. Teevan, and S.T. Iqbal. Optimizing for Happiness and Productivity: Modeling Opportune Moments for Task Transitions and Breaks at Work. In Proceedings of the ACM Conference on Human Factors in Computing Systems (CHI 2020)