I am Messi H.J. Lee, a researcher in machine psychology — a field dedicated to understanding the behavior and reasoning of AI systems through a psychological lens. I earned my PhD in Computational and Data Sciences from Washington University in St. Louis in May 2025, co-advised by Calvin K. Lai and Jacob M. Montgomery.

My research asks not just what models do, but why they behave the way they do — using frameworks from social psychology to study how AI systems develop and display human-like biases. My earlier work examined homogeneity bias in large language models, quantifying LLMs' tendency to represent marginalized groups as more homogeneous than their dominant counterparts. More recently, I have been studying implicit bias-like patterns in reasoning models — specifically, their tendency to consume more reasoning tokens when processing association-incompatible information compared to association-compatible information.

Outside the lab, I read mostly fiction and visit art exhibits. I am currently reading See Friendship by Jeremy Gordan — a book I came across in a bookstore on Delmar Loop in St. Louis, Missouri, shortly after completing my dissertation. After 28 years of not driving, I decided it was time and enrolled in a driving academy, where I practice on simulators. I expect to take my first road trip in June 2026.

I am currently completing my mandatory military service in South Korea as technical research personnel (전문연구요원), developing AI for pathology. As part of the R&D team at a company preparing for IPO, my core responsibilities include regulatory submissions to the MFDS (Ministry of Food and Drug Safety) for AI models covering lymph node metastasis in breast cancer, HRD testing in ovarian cancer, and mitosis detection across five cancer types. I am also responsible for all technical patents related to our services and models.

My service ends in June 2028, after which I may continue in my current role as part of a global expansion into markets such as the US, or pursue new opportunities that come my way.

I am open to collaborations on AI in general, particularly on AI bias and machine psychology. I am currently working on projects examining prototypicality bias in Vision-Language Models — studying how the prototypicality of faces shapes AI stereotyping behavior — and on social dynamics between agents in multi-agent simulations.

Don't hesitate to reach me at messihjlee[at]gmail.com