@article{stackelberglearningfromhumanfeedbackpref,
  title = {Stackelberg Learning from Human Feedback: Preference Optimization as a Sequential Game},
  author = {Barna Pásztor and Thomas Kleine Buening and Andreas Krause},
  year = {2025},
  eprint = {2512.16626},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2512.16626},
}