@article{alarmalignlanguagemodelsviahierarchical,
  title = {ALaRM: Align Language Models via Hierarchical Rewards Modeling},
  author = {Yuhang Lai and Siyuan Wang and Shujun Liu and Xuanjing Huang and Zhongyu Wei},
  year = {2024},
  eprint = {2403.06754},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2403.06754v2},
}