@inproceedings{he-etal-2024-semi-supervised,
    title = "Semi-Supervised Reward Modeling via Iterative Self-Training",
    author = "He, Yifei  and
      Wang, Haoxiang  and
      Jiang, Ziyan  and
      Papangelis, Alexandros  and
      Zhao, Han",
    editor = "Al-Onaizan, Yaser  and
      Bansal, Mohit  and
      Chen, Yun-Nung",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
    month = nov,
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2024.findings-emnlp.434/",
    doi = "10.18653/v1/2024.findings-emnlp.434",
    pages = "7365--7377"
}