publications

2026

  1. ICML
    PLOT: Progressive Localization via Optimal Transport in Neural Causal Abstraction
    Jonathn Chang, Arya Datla, and Ziv Goldfeld
    ICML Workshop for Mechanistic Interpretability, 2026.
    arXiv Code
  2. ICML
    Side Effects of Character Training: Quantifying Cross-Constitution Drift in LLMs
    Bhagyesh Kumar, Ananya Sutradhar, Saurav Panigrahi, Jonathn Chang, and Lionel Levine
    Work done as a research mentor for SPAR.
    ICML Workshop for Pluralistic Alignment, 2026.
    Paper
  3. ICLR
    EigenBench: A Comparative Behavioral Measure of Value Alignment
    Jonathn Chang, Leonhard Piff, Suvadip Sana, Jasmine X. Li, and Lionel Levine
    ICLR, 2026. Oral (top 1.13%).
    arXiv Code

2023

  1. IEEE
    Hate speech and hate crimes: a data-driven study of evolving discourse around marginalized groups
    Malvina Bozhidarova*, Jonathn Chang*, Aaishah Ale-rasool, Yuxiang Liu, Chongyao Ma, Andrea L. Bertozzi, P. Jeffrey Brantingham, Junyuan Lin, and Sanjukta Krishnagopal
    IEEE International Conference on Big Data, 2023.
    arXiv