@article{improvingmachinetranslationwithhuman,
  title = {Improving Machine Translation with Human Feedback: An Exploration of Quality Estimation as a Reward Model},
  author = {Zhiwei He and Xing Wang and Wenxiang Jiao and Zhuosheng Zhang and Rui Wang and Shuming Shi and Zhaopeng Tu},
  year = {2024},
  eprint = {2401.12873},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2401.12873v3},
}