@inproceedings{lai-etal-2024-alarm,
    title = "{AL}a{RM}: Align Language Models via Hierarchical Rewards Modeling",
    author = "Lai, Yuhang  and
      Wang, Siyuan  and
      Liu, Shujun  and
      Huang, Xuanjing  and
      Wei, Zhongyu",
    editor = "Ku, Lun-Wei  and
      Martins, Andre  and
      Srikumar, Vivek",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2024",
    month = aug,
    year = "2024",
    address = "Bangkok, Thailand",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/2024.findings-acl.465/",
    doi = "10.18653/v1/2024.findings-acl.465",
    pages = "7817--7831"
}