Articles in conference proceedings

• A. Pan, E. Jones, M. Jagadeesan, and J. Steinhardt, "Feedback Loops With Language Models Drive In-Context Reward Hacking," in Forty-first International Conference on Machine Learning, ICML'24, 2024.
• M. Jagadeesan, A. Wei, M. Jordan, and J. Steinhardt, "Learning equilibria in matching markets from bandit feedback," in Advances in Neural Information Processing Systems, 2021.

Masters Reports

• D. Halawi, A. Wei, E. Wallace, T. Wang, N. Haghtalab, and J. Steinhardt, "Covert Malicious Finetuning: Challenges in Safeguarding LLM Adaption," EECS Department, University of California, Berkeley, Tech. Rep. UCB/EECS-2024-216, Dec. 2024.
• Z. Yang, Y. Ma, and J. Steinhardt, "Interpolation Learning," EECS Department, University of California, Berkeley, Tech. Rep. UCB/EECS-2021-51, May 2021.