@inproceedings{ alazraki2025reverse, title={Reverse Engineering Human Preferences with Reinforcement Learning}, author={Lisa Alazraki and Yi-Chern Tan and Jon Ander Campos and Maximilian Mozes and Marek Rei and Max Bartolo}, booktitle={The Thirty-ninth Annual Conference on Neural Information Processing Systems}, year={2025}, url={https://openreview.net/forum?id=heY0zzGvYm} }