I am a second-year Ph.D. student in Computer Science at Indiana University Indianapolis, advised by Prof. Hyeju Jang. My research focuses on the reliability of language understanding in large language models. I study when models’ judgments and responses reflect the meaning of a text, and when they are sensitive to how that meaning is expressed. My recent work examines this question through metaphor and discourse coherence. In ongoing work, I investigate how models preserve uncertainty in language and use representation analysis to explore the internal processes underlying their behavior.

🔍 I am seeking research internship opportunities for Summer 2027 in LLM evaluation, reliability, and interpretability.

🔥 News

  • 2026.06:  🎉 Our paper “A Mirage of Coherence: How Metaphor Impacts Language Models’ Discourse Coherence Assessment” has been accepted to COLM 2026 and selected for an Oral Spotlight Presentation!

📝 Publications

For a complete list of publications, please see my Google Scholar.

📖 Educations

  • 2025.08 - Present, Ph.D. Student, Computer Science, Indiana University Indianapolis.
  • 2022.08 - 2025.06, M.S. in Computer Technology, Dalian University of Technology.