@article{isonpolicydataalwaysthebestchoicefordire,
  title = {Is On-Policy Data always the Best Choice for Direct Preference Optimization-based LM Alignment?},
  author = {Zetian Sun and Dongfang Li and Xuhui Chen and Baotian Hu and Min Zhang},
  year = {2025},
  eprint = {2508.10530},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2508.10530},
}