@article{weaktostrongpreferenceoptimization,
  title = {Weak-to-Strong Preference Optimization: Stealing Reward from Weak Aligned Model},
  author = {Wenhong Zhu and Zhiwei He and XiaoFeng Wang and PengFei Liu and Rui Wang},
  year = {2024},
  eprint = {2410.18640},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2410.18640v1},
}