I am a Ph.D. student in Data Science at Seoul National University, advised by Prof. Yohan Jo. I received my B.S. in Computer Science and Engineering from SNU.
My research interests lie in artificial intelligence, with a focus on building reliable and human-aligned LLM systems. In particular, I study:
interpretability and model surgery through representation analysis, with the goal of detecting and controlling diverse failure modes of large language models
human alignment of LLM systems, with the goal of aligning models with human values while respecting the plurality of individual preferences and perspectives