@article{pilafoptimalhumanpreferencesamplingfor,
  title = {PILAF: Optimal Human Preference Sampling for Reward Modeling},
  author = {Yunzhen Feng and Ariel Kwiatkowski and Kunhao Zheng and Julia Kempe and Yaqi Duan},
  year = {2025},
  eprint = {2502.04270},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2502.04270v1},
}