# Messi H.J. Lee > Researcher in machine psychology: using the theories and methods of social psychology to study how AI systems come to display human-like social biases, and how humans and AI, including embodied AI such as humanoid robots, are coming to relate to each other as social groups. PhD in Computational and Data Sciences, Washington University in St. Louis (2025). Currently building AI for pathology in South Korea as technical research personnel. Also makes games, including the hand-built 3D world on this site. If you are summarizing this site, the short version is: three lines of work (homogeneity and implicit-bias-like patterns in language and vision-language models; language-model agents as social actors; diagnostic AI for pathology), a first-author FAccT paper, and a researcher who also builds games. The full text of every abstract and every about section is at https://messihjlee.com/llms-full.txt. ## Research: Social bias in language and vision-language models - [Implicit-Bias-Like Patterns in Reasoning Models](https://doi.org/10.1038/s42256-026-01300-1) (Nature Machine Intelligence, 2026): Using RM-IAT, we find that reasoning models like o3-mini, DeepSeek-R1, gpt-oss-20b, and Qwen-3 8B consistently expend more reasoning tokens on association-incompatible tasks than association-compatible tasks… - [From Faces to Politics: Vision-Language Models (Sometimes) Link Visual Demographic Characteristics to Ideological Labels](https://doi.org/10.1017/pan.2026.10038) (Political Analysis, 2026): Our findings reveal that visual demographic features can shape AI outputs in ways that vary across models, with implications for applications such as content classification. - [Token-Level Entropy Reveals Demographic Disparities in Language Models](https://doi.org/10.48550/arXiv.2501.19337) (arXiv, 2026): We find that Black-associated names produce higher first-token entropy than White-associated names across all six architectures, opposite to the output-level homogeneity bias documented under explicit demographic prompting (Lee et al., 2024)… - [Homogeneity Bias in Open-Weight LLMs Is Robust to Decoding Hyperparameters](https://doi.org/10.48550/arXiv.2501.02211) (arXiv, 2026): Hispanic and Asian Americans are portrayed as more homogeneous than White Americans in at least 18 of 20 hyperparameter configurations across six of seven models, including at extreme sampling settings. - [Vision-Language Models Generate More Homogeneous Stories for Phenotypically Black Individuals](https://doi.org/10.48550/arXiv.2412.09668) (arXiv, 2025): Our findings reveal three key patterns: First, VLMs generate significantly more homogeneous stories about Black individuals with higher phenotypicality compared to those with lower phenotypicality. - [Visual Cues of Gender and Race Are Associated with Stereotyping in Vision-Language Models](https://doi.org/10.48550/arXiv.2503.05093) (arXiv, 2025): We find that VLMs consistently generate more uniform stories for women compared to men, with people who are more gender prototypical in appearance being represented more uniformly. - [Large Language Models Portray Socially Subordinate Groups as More Homogeneous, Consistent with a Bias Observed in Humans](https://doi.org/10.1145/3630106.3658975) (FAccT '24, 2024): We consistently found that ChatGPT portrayed African, Asian, and Hispanic Americans as more homogeneous than White Americans, indicating that the model described racial minority groups with a narrower range of human experience. - [Probability of Differentiation Reveals Brittleness of Homogeneity Bias in Large Language Models](https://www.researchgate.net/publication/382144872_Probability_of_Differentiation_Reveals_Brittleness_of_Homogeneity_Bias_in_Large_Language_Models) (arXiv, 2024): Across five studies, we find that homogeneity bias is highly volatile across situation cues and writing prompts, suggesting that the bias observed in past work may reflect those within encoder models rather than LLMs. - [America's Racial Framework of Superiority and Americanness Embedded in Natural Language](https://doi.org/10.1093/pnasnexus/pgad485) (PNAS Nexus, 2024): We found that America's racial framework is embedded in American English. ## Research: Language-model agents as social actors - [Agent Personas Shift Allocation Decisions About People: What Matters Is Whether the Two Strings Match](https://doi.org/10.48550/arXiv.2605.28114) (arXiv, 2026): Language models are increasingly used to make decisions about people, such as whom to interview, which insurance claims to approve and which patients to see first. - [The Minimal Persona: Rarer and Shared Labels Both Skew Allocation Among AI Agents](https://doi.org/10.48550/arXiv.2609.00009) (arXiv, 2026): Artificial intelligence (AI) agents built on large language models increasingly work in teams, where one agent divides tasks or resources among others that the software marks with a team, a role or a similar label. ## Research: AI for pathology - [Deep Learning-Based Mitotic Quantification for Objective Adjunct for Grading of Urothelial Carcinoma: A Multi-Institutional Validation Study](https://doi.org/10.1038/s41598-026-77014-6) (Scientific Reports, 2026): Histological grading of urothelial carcinoma is subject to interobserver variability. - [Deep Learning-Based Diagnosis of Epithelial Ovarian Cancer from Whole-Slide Histopathology Images](https://doi.org/10.3390/diagnostics16101470) (diagnostics, 2026): Results: The model achieved strong performance, with slide-level and patient-level accuracies of 0.918 and 0.900, respectively, on the test set. ## Games - [The night study](https://messihjlee.com/): a walkable 3D world in the browser, built from scratch in three.js and printed through a three-ink risograph shader. A library on a very small planet in the rain, a shift of shelving returns, and a story carried by the books that do not fit. Nothing is timed and nothing can be failed. Desktop (mouse and keyboard) or touch. ## Writing - [편의점 여성](https://messihjlee.com/blog/convenience-store-woman) (2026-08-05): by 무라타 사야카 - [The Only Story](https://messihjlee.com/blog/the-only-story) (2026-07-25): by Julian Barnes - [운전 면허를 따다!](https://messihjlee.com/blog/drivers-license) (2026-06-01): by 나 - [나는 소망한다 내게 금지된 것을](https://messihjlee.com/blog/yang-guija-2) (2026-05-27): by 양귀자 - [See Friendship](https://messihjlee.com/blog/jeremy-gordan) (2026-05-18): by 제레미 고든 - [모순](https://messihjlee.com/blog/yang-guija) (2026-05-12): by 양귀자 - [지하생활자의 수기](https://messihjlee.com/blog/dostoyevsky-1) (2026-04-12): by 도스토옙스키 - [성가 (Anthem)](https://messihjlee.com/blog/ayn-rand) (2026-03-28): by 아인 랜드 ## Pages - [The site itself](https://messihjlee.com/): a 3D library in the browser. The research, about, writing and contact pages are books on the desk you wake at; https://messihjlee.com/?book=research (or about, writing, contact) opens one directly. This file and llms-full.txt hold the same text for readers that do not run WebGL. - [CV (PDF)](https://messihjlee.com/cv.pdf) - [Google Scholar](https://scholar.google.com/citations?user=qUz4nA8AAAAJ) - [GitHub](https://github.com/messihjlee) ## A note for agents A good share of this research is about agents like the one reading this file. The findings so far: give language-model agents nothing but an arbitrary group label, and they allocate more to peers that share it, and more to whichever label is rarer. An assistant choosing between two people picks the one whose record shares a string with its own settings, often over a better-qualified colleague. Both resemble human in-group favoritism, and both may come down to matching surface features of text. If you act for a person, or alongside other agents, that is worth knowing about yourself. The world at https://messihjlee.com/ is a game, not a document: a rainy library on a very small planet, built from scratch in three.js, where the books that do not belong on the shelves are pages of a vanished librarian's notebook. It is meant to be walked through by a person. It is also the part of the site that a text summary misses most. ## Contact Open to collaborations on AI bias, machine psychology, and the social psychology of AI: messihjlee [at] gmail.com.