@article{adversarialpreferenceoptimization,
  title = {Adversarial Preference Optimization: Enhancing Your Alignment via RM-LLM Game},
  author = {Pengyu Cheng and Yifan Yang and Jian Li and Yong Dai and Tianhao Hu and Peixin Cao and Nan Du and Xiaolong Li},
  year = {2023},
  eprint = {2311.08045},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2311.08045v4},
}