The Feasibility of a Hardwired Pause of Frontier AI Training
with Will Fithian, Kayla Blomquist, Gregory Conti, Barry Eichengreen, Rose Gottemoeller, Kelly M. Greenhill, Ming-Yen Ho, Thomas Icard, Shachar Kariv, Daniel Kroth, David Krueger, Gretchen Krueger, Erik Leklem, Adam Lesnikowski, Xiaobo Lü, Dennis Murphy, Lindsay Rand, Andrew Reddie, Stuart Russell, Daniel Sargent, Kirsten Ann Schulz, Sanjit Seshia, Anita Srinivasan, Rory Truex, Carah Ong Whaley
2026. In progress.
Social Choice Should Guide AI Alignment in Dealing with Diverse Human Feedback
with Vincent Conitzer, Rachel Freedman, Jobst Heitzig, Bob M. Jacobs, Nathan Lambert, Milan Mossé, Eric Pacuit, Stuart Russell, Hailey Schoelkopf, Emanuel Tewolde, and William S. Zwicker
2024. International Conference on Machine Learning.
Learning to Manipulate under Limited Information
with Alexander Kristoffersen and Eric Pacuit
Forthcoming in Proceedings of the 39th Annual AAAI Conference on Artificial Intelligence (AAAI 2025).
Accepted for the 1st Workshop on Social Choice and Learning Algorithms (SCaLA 2024) held at AAMS 2024.
Conditional and Modal Reasoning in Large Language Models
with Cedegao Zhang and Matthew Mandelkern
2024. Empirical Methods in Natural Language Processing (EMNLP).