About

I’m a postdoctoral fellow at Harvard University as part of the Harvard Data Science Initiative. I work on behavioral machine learning: developing tools to evaluate how AI models understand the world so we can create shared understanding between models and people. I’m also an affiliate with LIDS at MIT.

I completed my PhD in computer science at Columbia University in 2023, where I was advised by David Blei. During my PhD, I was an NSF GRFP Fellow and Cheung-Kong Innovation Doctoral Fellow. Upon graduating, I received the Morton B. Friedman Memorial Prize for excellence in engineering.

Here is my curriculum vitae.

Email: kvafa AT g.harvard.edu

Selected Papers

Estimating Wage Disparities Using Foundation Models
K Vafa, S Athey, D Blei
Proceedings of the National Academy of Sciences (PNAS), 2025 [to appear]
[PNAS] [arXiv]

Evaluating the World Model Implicit in a Generative Model
K Vafa, J Y Chen, A Rambachan, J Kleinberg, S Mullainathan
Neural Information Processing Systems (NeurIPS), 2024 [spotlight]
[Paper] [Code] [Twitter summary] Press: Nature, MIT News, Wall Street Journal

Do Large Language Models Perform the Way People Expect? Measuring the Human Generalization Function
K Vafa, A Rambachan, S Mullainathan
International Conference on Machine Learning (ICML), 2024
[Paper] [Code] [MIT News]

CAREER: A Foundation Model for Labor Sequence Data
K Vafa, E Palikot, T Du, A Kanodia, S Athey, D Blei
Transactions of Machine Learning Research (TMLR), 2023
[Paper] [Code] [Podcast] [Video]

Revisiting Topic-Guided Language Models
C Zheng, K Vafa, D Blei
Transactions of Machine Learning Research (TMLR), 2023
[Paper]

An Invariant Learning Characterization of Controlled Text Generation
C Zheng, C Shi, K Vafa, A Feder, D Blei
Association for Computational Linguistics (ACL), 2023
[Paper] [Code]

Interpretable Machine Learning for the Social Sciences: Applications in Political Science and Labor Economics
K. Vafa
Ph.D. Thesis, 2023
[Paper]

Rationales for Sequential Predictions
K Vafa, Y Deng, D Blei, A Rush
Empirical Methods in Natural Language Processing (EMNLP), 2021
[Paper] [Code] [Colab Notebook] [Video]

Assessing the Effects of Friend-to-Friend Texting on Turnout in the 2018 U.S. Midterm Elections
A Schein, K Vafa, D Sridhar, V Veitch, J Quinn, J Moffet, D Blei, D Green
The Web Conference (WWW), 2021
[Paper]

Text-Based Ideal Points
K Vafa, S Naidu, D Blei
Association for Computational Linguistics (ACL), 2020
[Paper] [Code] [Colab Notebook] [Video] [Interactive Figures]

Discrete Flows: Invertible Generative Models of Discrete Data
D Tran, K Vafa, K Agrawal, L Dinh, B Poole
Neural Information Processing Systems (NeurIPS), 2019
[Paper]