@article{iterativenashpolicyoptimizationaligning,
  title = {Iterative Nash Policy Optimization: Aligning LLMs with General Preferences via No-Regret Learning},
  author = {Yuheng Zhang and Dian Yu and Baolin Peng and Linfeng Song and Ye Tian and Mingyue Huo and Nan Jiang and Haitao Mi and Dong Yu},
  year = {2024},
  eprint = {2407.00617},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2407.00617v4},
}