@article{limitedpreferencedatalearningbetterrewar,
  title = {Limited Preference Data? Learning Better Reward Model with Latent Space Synthesis},
  author = {Leitian Tao and Xuefeng Du and Sharon Li},
  year = {2025},
  eprint = {2509.26074},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2509.26074},
}