@article{acceleratingrlhftrainingwithreward,
  title = {Accelerating RLHF Training with Reward Variance Increase},
  author = {Zonglin Yang and Zhexuan Gu and HouDuo Qi and Yancheng Yuan},
  year = {2025},
  eprint = {2505.23247},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2505.23247v2},
}