@article{sequencetosequencerewardmodeling,
  title = {Sequence to Sequence Reward Modeling: Improving RLHF by Language Feedback},
  author = {Jiayi Zhou and Jiaming Ji and Juntao Dai and Yaodong Yang},
  year = {2024},
  eprint = {2409.00162},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2409.00162v1},
}