@article{sentencelevelrewardmodelcangeneralize,
  title = {Sentence-level Reward Model can Generalize Better for Aligning LLM from Human Preference},
  author = {Wenjie Qiu and Yi-Chen Li and Xuqin Zhang and Tianyi Zhang and Yihang Zhang and Zongzhang Zhang and Yang Yu},
  year = {2025},
  eprint = {2503.04793},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2503.04793v4},
}