@article{onebiasafteranothermechanisticrewardshap,
  title = {One Bias After Another: Mechanistic Reward Shaping and Persistent Biases in Language Reward Models},
  author = {Daniel Fein and Max Lamparth and Violet Xiang and Mykel J. Kochenderfer and Nick Haber},
  year = {2026},
  eprint = {2603.03291},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2603.03291},
}