@article{scalableensemblingformitigatingreward,
  title = {Scalable Ensembling For Mitigating Reward Overoptimisation},
  author = {Ahmed M. Ahmed and Rafael Rafailov and Stepan Sharkov and Xuechen Li and Sanmi Koyejo},
  year = {2024},
  eprint = {2406.01013},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2406.01013v2},
}