@article{stepdpostepwisepreferenceoptimization,
  title = {Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs},
  author = {Xin Lai and Zhuotao Tian and Yukang Chen and Senqiao Yang and Xiangru Peng and Jiaya Jia},
  year = {2024},
  eprint = {2406.18629},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2406.18629v1},
}