@article{explicitpreferenceoptimizationnoneedfor,
  title = {Explicit Preference Optimization: No Need for an Implicit Reward Model},
  author = {Xiangkun Hu and Lemin Kong and Tong He and David Wipf},
  year = {2025},
  eprint = {2506.07492},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2506.07492v1},
}