MTS is the department’s Mind, Technology, and Society speaker series. It is hosted by a different faculty member each semester. Founded by a generous gift from Professors Robert Glushko and Pamela Samuelson, MTS brings researchers and industry professionals from across the globe to present a variety of interdisciplinary work in cognitive science. See our UCMerced CogSci youtube channel for videos of past MTS talks!
CIS graduate students, faculty, and staff, and all who are interested are invited! Members of other departments at UC Merced as well as the general public are encouraged to attend. (Note: current CIS Ph.D. students are required to attend MTS each semester in residence, to fulfill their COGS 250 course requirement).
Dr. Leilani Gilpin talk "Finding the Right Explanations: From Neurons to Complex, Real-World AI Systems" will be from 2-3:30pm in SSM 104.
Abstract: As AI systems are increasingly deployed in high-stakes and human-centered settings, there will be some explaining to do. However, a fundamental question remains underexplored: what makes an explanation the "right" one? In this talk, I will present a unifying perspective on explanation across four domains at different levels in the AI pipeline. At the neural level, I introduce compositional explanations across the full activation range. At the model level, I examine large language models and show how explanations can be grounded in formal logic to detect inconsistencies and hallucinations. At the human level, I explore visually impaired users interacting with vision-language models, where explanations must guide actions: such as how to reframe a question or reorient a camera. To conclude, I will discuss ongoing work to develop explanations at the system level, specifically in the domain of autonomous driving. This motivates the use of explanations to support safety-critical systems for diagnosis, system-debugging, and accountability.
Bio: Leilani H. Gilpin is an Assistant Professor in the Department of Computer Science and Engineering at UC Santa Cruz. Her research focuses on the design and analysis of methods for autonomous systems to explain themselves. Her work has applications to robust decision-making, system debugging, and accountability. She holds a PhD in Computer Science from MIT, an M.S. in Computational and Mathematical Engineering from Stanford University, and a B.S. in Mathematics (with honors), B.S. in Computer Science (with highest honors), and a music minor from UC San Diego. Outside of research, Leilani enjoys swimming, cooking, hiking, emacs, and org mode.
For more information or to sign up for email announcements, please contact the talk series organizer: cis-mts-lead@lists.ucmerced.edu.
