@article{debiasingrewardmodelsbyrepresentationlea,
  title = {Debiasing Reward Models by Representation Learning with Guarantees},
  author = {Ignavier Ng and Patrick Blöbaum and Siddharth Bhandari and Kun Zhang and Shiva Kasiviswanathan},
  year = {2025},
  eprint = {2510.23751},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2510.23751},
}