@article{looselipssinkshipsmitigatinglengthbias,
  title = {Loose lips sink ships: Mitigating Length Bias in Reinforcement Learning from Human Feedback},
  author = {Wei Shen and Rui Zheng and WenYu Zhan and Jun Zhao and Shihan Dou and Tao Gui and Qi Zhang and Xuanjing Huang},
  year = {2023},
  eprint = {2310.05199},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2310.05199v5},
}