Lucius EJ Bynum

I am a PhD Candidate at the NYU Center for Data Science co-advised by Julia Stoyanovich as part of the Center for Responsible AI and by Joshua Loftus at the London School of Economics. In my dissertation research, I have also had the pleasure of working with Kyunghyun Cho and Jennifer Hill.

I do research at the intersection of causal inference (CI) and artificial intelligence (AI). This work includes developing tools for inequality-aware decision making and more wholistic algorithmic fairness, leveraging counterfactual reasoning to improve model explainability and reduce pre-existing disparities, and reimagining how we use causal modeling formalisms to approach AI problems involving demographic data. It also includes combining CI and AI tools (like language models and structural causal models) to fundamentally improve average as well as heterogeneous treatment effect estimation.

I am also passionate about teaching via public outreach and making educational material in these areas.

My research is generously supported by the Microsoft Research PhD Fellowship.

news

Nov 13, 2024 New preprint release: Language Models as Causal Effect Generators.
Oct 08, 2024 Paper accepted at NeurIPS 2024! Causal Dependence Plots.
Aug 03, 2024 Paper accepted for oral presentation at IJCAI 2024! A New Paradigm for Counterfactual Reasoning in Fairness and Recourse.
Apr 11, 2024 Nominated for the 2024 Future Leaders Summit on Responsible Data Science and AI! Thank you to the Michigan Institute for Data Science (MIDAS) and to all attendees for a great symposium!
Jan 25, 2024 New preprint release: A New Paradigm for Counterfactual Reasoning in Fairness and Recourse.

selected publications

  1. densities_square.png
    Counterfactuals for the Future
    Lucius EJ Bynum ,  Joshua R Loftus ,  and  Julia Stoyanovich
    Proceedings of the AAAI Conference on Artificial Intelligence, Jun 2023
  2. sdscm_square.png
    Language Models as Causal Effect Generators
    Lucius EJ Bynum ,  and  Kyunghyun Cho
    arXiv Preprint arXiv:2411.08019, Jun 2024