Christine P Lee
PhD Student @ University of Wisconsin-Madison, Department of Computer Sciences
Hi there! I’m a third-year Ph.D. student, advised by Professor Bilge Mutlu.
I develop human-centered AI systems that combine black box AI models (i.e., large language models (LLMs)) with formal methods and models—such as verification, synthesis, and Markov Decision Processes—to make AI outputs verifiable, adaptable, and repairable. My work tackles challenges users face when AI is deployed in real-world settings, including unreliable verification, limited adaptability, and misaligned expectations.
By integrating deterministic checks, persistent constraints, and transparent reasoning into AI workflows, I aim to reduce oversight burden, make user control more expressive, and ensure AI systems adapt smoothly to changing needs. My five research pillars—Verify, Constrain, Observe, Adapt, and Bridge—guide this work toward AI that is reliable, transparent, and seamlessly embedded in human workflows.
My research is supported by the Cisco Distinguished Graduate Fellowship and the NSF INTEGRATE Research Training Program Fellowship.
selected publications
- CHI’22
The unboxing experience: Exploration and design of initial interactions between children and social robotsIn Proceedings of the 2022 CHI conference on human factors in computing systems, 2022
