NCSA Calendar
NCSA staff who would like to submit an item for the calendar can email newsdesk@ncsa.illinois.edu.
Machine Learning Seminar: Yuji Zhang "Knowledge is Power, But Power Casts Shadows?"
Feb 20, 2026 2:00 - 3:15 pm
1214 Siebel Center
- Sponsor
- Research Area of Artificial Intelligence
- Speaker
- Yuji Zhang
- Contact
- Allison Mette
- agk@illinois.edu
- Views
- 12
- Originating Calendar
- Siebel School Speakers Calendar
- Abstract: Knowledge is a prerequisite for intelligent behavior. Although modern language models acquire substantial knowledge and can leverage it to solve tasks with superior performance, the underlying mechanisms often remain opaque and fragile. This talk presents knowledgeable foundation models for robust intelligence and asks: What does the model know? When and why does it fail? How can we update it with minimal trade-off? And how do we use it to reason and ultimately to optimize decisions?First, we make model knowledge explicit and testable and investigate why unreliable knowledge emerges, covering hallucination and staleness. We identify knowledge overshadowing, interactions among individually correct pieces of knowledge that are miscomposed and trigger hallucinations, and we quantify and even foresee such failures to gain greater model controllability and robustness. These diagnoses drive targeted, localized repairs that bound side effects. Second, we operationalize knowledge as interpretable, composable atomic skills, enabling modular reasoning that strengthens generalization and robustness. Finally, we translate interpretable knowledge into decision value by aligning reasoning with downstream utility. Together, these pieces advance foundation models toward greater interpretability, controllability, and reliability, pointing toward robust intelligence grounded in knowledge.Bio: Yuji Zhang is a postdoctoral researcher at the University of Illinois Urbana-Champaign, advised by Prof. Heng Ji and Prof. Chengxiang Zhai. She received her Ph.D. in Computer Science from Hong Kong Polytechnic University. Her research focuses on building robust and trustworthy foundation models by investigating the lifecycle of knowledge, including how knowledge is acquired, represented, updated, and applied, and how these mechanisms shape model behavior. Her work has been published in top-tier conferences, including ACL, EMNLP, ICLR, etc. She organized the AAAI 2025 tutorial on the knowledge lifecycle of LLMs and the ACL 2025 workshop on knowledgeable foundation models.