@inproceedings{he-etal-2024-improving,
    title = "Improving Machine Translation with Human Feedback: An Exploration of Quality Estimation as a Reward Model",
    author = "He, Zhiwei  and
      Wang, Xing  and
      Jiao, Wenxiang  and
      Zhang, Zhuosheng  and
      Wang, Rui  and
      Shi, Shuming  and
      Tu, Zhaopeng",
    editor = "Duh, Kevin  and
      Gomez, Helena  and
      Bethard, Steven",
    booktitle = "Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
    month = jun,
    year = "2024",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2024.naacl-long.451/",
    doi = "10.18653/v1/2024.naacl-long.451",
    pages = "8164--8180"
}