@article{onthelimitedgeneralizationcapabilityof,
  title = {On the Limited Generalization Capability of the Implicit Reward Model Induced by Direct Preference Optimization},
  author = {Yong Lin and Skyler Seto and Maartje ter Hoeve and Katherine Metcalf and Barry-John Theobald and Xuan Wang and Yizhe Zhang and Chen Huang and Tong Zhang},
  year = {2024},
  eprint = {2409.03650},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2409.03650v2},
}