@article{reverseengineeringhumanpreferenceswith,
  title = {Reverse Engineering Human Preferences with Reinforcement Learning},
  author = {Lisa Alazraki and Tan Yi-Chern and Jon Ander Campos and Maximilian Mozes and Marek Rei and Max Bartolo},
  year = {2025},
  eprint = {2505.15795},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2505.15795v1},
}