Minwoo (Josh) Kang


prof_pic.jpg

I’m a fifth-year PhD student in Computer Science at UC Berkeley, where I am affiliated with Berkeley AI Research (BAIR) and the SLICE Lab.
My research is advised by John Canny and John Wawrzynek.

My research spans various topics in language modeling and NLP, with applications in computational social science as well as language models as ‘‘agents’’.

Most recent interests:

  • Language models as collaborative agents
    • How do we train models that infer beliefs & intentions of the user and generate language conditioned on latent intents for effective Human-AI collaboration?
  • Language models as exploratory agents
    • How do we equip models with the ability to propose and test hypotheses, especially under environments with high uncertainty or underspecification of constraints, and effectively search over a space of viable solutions?
  • Language models as models of human behavior
    • How do we condition models to approximate human users with high fidelity, and how should we rethink LLM post-training for such applications in studying human behavior?


For contact, please reach out to:
mkang at cs dot {my institution} dot edu

news

Feb 28, 2025 Check out our new preprint “Language Model Fine-Tuning on Scaled Survey Data for Predicting Distributions of Public Opinions”! Link to X thread → :thread:.
Nov 08, 2024 :airplane: I will be attending EMNLP 2024 to present our work “Virtual Personas for Language Models via an Anthology of Backstories”. Looking forward to presenting our poster!

selected publications

  1. Language Model Fine-Tuning on Scaled Survey Data for Predicting Distributions of Public Opinions
    Joseph Suh* ,  Erfan Jahanparast* ,  Suhong Moon* ,  Minwoo Kang* ,  and  Serina Chang
    arXiv preprint arXiv:2502.16761, 2025
  2. Virtual Personas for Language Models via an Anthology of Backstories
    Suhong Moon* ,  Marwa Abdulhai* ,  Minwoo Kang* ,  Joseph Suh ,  Widyadewi Soedarmadji , and 3 more authors
    In 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP) , 2024
  3. Rediscovering the Latent Dimensions of Personality with Large Language Models as Trait Descriptors
    Joseph Suh* ,  Suhong Moon* ,  Minwoo Kang* ,  David M Chan ,  and  John Canny
    In 2024 NeurIPS Workshop on Behavioral ML , 2024
  4. FVEval: Understanding Language Model Capabilities in Formal Verification of Digital Hardware
    Minwoo Kang ,  Mingjie Liu ,  Ghaith Bany Hamad ,  Syed Suhaib ,  and  Haoxing Ren
    In (To Appear) 2025 Design, Automation & Test in Europe Conference & Exhibition (DATE) Focus Session , 2025