PhD StudentAI Researcher
I am a Ph.D. student at KAIST AI.
My research explores how large language models represent, reason over, and revise knowledge, with a particular focus on non-monotonic reasoning, belief revision, and learning under changing information. I study how models maintain or update their beliefs when evidence is introduced, contradicted, or retracted, and how they resolve conflicts among competing rules, constraints, and sources of information.
I combine formal approaches to knowledge representation and reasoning with empirical studies of language models, including interpretability and learning-based methods. My goal is to understand how models acquire and maintain structured knowledge, adapt to changing evidence, and make consistent decisions under conflicting information.
With a background in mathematics, computer science, and AI (B.S. in Mathematics and Software Engineering; M.S. in AI), I aim to develop AI systems that can reason reliably, revise their knowledge appropriately, and act consistently with evidence and constraints.
Research interests: Non-monotonic Reasoning, Belief Revision, Learning under Changing Knowledge, Interpretability, AI Safety
News
Loading updates...