PhD Student | AI Researcher
I am a Ph.D. student at KAIST AI, advised by Prof. Jaesik Choi.
My research studies knowledge structure in logic, AI, and human reasoning, with a focus on how constraints are represented and resolved in large language models. I investigate how such structures are realized within model computations, combining mechanistic interpretability (neuron- and circuit-level analysis) with constraint-aware modeling.
My work aims to understand how models represent requirements, resolve conflicts, and produce behavior consistent with structured knowledge and user intent. Grounded in training across mathematics, computer science, and AI (B.S. in Mathematics and Computer Science, M.S. in AI), I build systems that are reliable, transparent, and robust in real-world settings.
Research interests: AI Safety, non-monotonic reasoning, constraint conflict, factuality
News
Loading updates...