prof_pic.jpg

Dang Nguyen

I am a Computer Science PhD student in the Chicago Human+AI Lab at the University of Chicago advised by Chenhao Tan. I also work with Ari Holtzman as part of a wider Communication & Intelligence initiative to study communication in the age of talking machines.

Lately, I have been thinking about LLM pragmatic reasoning, how they can coordinate, persuade, and inspire us in economic collaborations beyond mere instruction following. This calls for more dynamic benchmarks, for which I see simulated environments, or communication games, as potential solutions. HR Simulator™ is the first game I built in this direction. I am also interested in LLM-human interaction, including uncovering and mitigating social biases in models’ decision-making.

Outside of research, you can find me practicing Brazilian Jiu Jitsu or lifting weights. If you think we have similar interests, feel free to reach out.

     

news

Oct 02, 2025 Presented HR Simulator™ at the Communication & Intelligence seminar.
Sep 26, 2025 We made an AI-driven communication puzzle game! HR Simulator™: Be the Person You Hate
Jul 07, 2025 LLM Representation Debiasing paper accepted at COLM 2025.

selected publications

  1. On the Effectiveness and Generalization of Race Representations for Debiasing High-Stakes Decisions
    Dang Nguyen, and Chenhao Tan
    In Conference on Language Modeling (COLM) , 2025
  2. Pragmatic radiology report generation
    Dang Nguyen, Chacha Chen, He He, and Chenhao Tan
    In Machine Learning for Health (ML4H) , 2023