Published multiple conference papers such as 'CUPID: Evaluating Personalized and Contextualized Alignment of LLMs from Interactions' and received the Best Paper Award at NAACL 2025.
Research Experience
Works with KIXLAB; will be a postdoctoral fellow at the University of Michigan CSE.
Education
Ph.D. student at the School of Computing, KAIST, working under the supervision of Juho Kim; will be joining the University of Michigan CSE as a postdoctoral fellow, working with Q. Vera Liao.
Background
Research interests lie in the intersection of human-AI interaction (HAI) and natural language processing (NLP), focusing on aligning AI systems with human cognitive processes to make them more adaptive, interpretable, and human-centered. Specifically, developing AI systems that interactively adapt their outputs to individual users by modeling human cognitive processes based on users' tasks and contexts, and designing evaluation methods to assess how effectively AI systems can generate outputs aligned with human cognitive processes.