About Me

I am a PhD student at Department of Philosophy, Carnegie Mellon University, fortunately co-advised by Prof. Kun Zhang and Prof. Peter Spirtes. I am also a member of the CMU-CLeaR Group.

Research Interests

I strive to advance trustworthy and responsible AI. In particular, I conduct research on algorithmic fairness to model and understand the social impact of computing technologies, and also causal learning and reasoning to further enhance the capacity of intelligent systems. As an ultimate goal, I would like to pursue the safe and principled development of machine intelligence with the help of causality, so that technologies can improve our lives in a responsible and effective way.

News

September 2024 I am awarded National Institute of Justice (NIJ) Graduate Research Fellowship. Thank you NIJ!
June 2024 Our paper “Detecting and Identifying Selection Structure in Sequential Data” is accepted to ICML 2024. We establish a set of identifiability results for selection structures in sequential data without any parametric assumptions or interventional experiments.
January 2024 Our paper “Procedural Fairness Through Decoupling Objectionable Data Generating Components” is accepted to ICLR 2024 (Spotlight). We reveal and address the often-overlooked issue of disguised procedural unfairness. Our proposal consists of the value instantiation rule and the appropriate reference point configurations.

Selected Publications

* denotes equal contribution

  1. arXivPreprint
    Steering LLMs Towards Unbiased Responses: A Causality-Guided Debiasing Framework
    arXiv Preprint, 2024.
  2. ICLRSpotlight
    Procedural Fairness Through Decoupling Objectionable Data Generating Components
    Zeyu TangJialu WangYang LiuPeter Spirtes, and Kun Zhang
    In Proceedings of the 12th International Conference on Learning Representations (preliminary version presented in NeurIPS 2023 AFT workshop), 2024.
  3. What-is and How-to for Fairness in Machine Learning: A Survey, Reflection, and Perspective
    Zeyu TangJiji Zhang, and Kun Zhang
    ACM Computing Surveys, 2023.
  4. Tier Balancing: Towards Dynamic Fairness over Underlying Causal Factors
    Zeyu TangYatong ChenYang Liu, and Kun Zhang
    In Proceedings of the 11th International Conference on Learning Representations (preliminary version presented in NeurIPS 2022 AFCP workshop), 2023.
  5. Attainability and Optimality: The Equalized Odds Fairness Revisited
    Zeyu Tang, and Kun Zhang
    In Proceedings of the 1st Conference on Causal Learning and Reasoning, 2022.