@article{stepcontrolleddpoleveragingstepwiseerror,
  title = {Step-Controlled DPO: Leveraging Stepwise Error for Enhanced Mathematical Reasoning},
  author = {Zimu Lu and Aojun Zhou and Ke Wang and Houxing Ren and Weikang Shi and Junting Pan and Mingjie Zhan and Hongsheng Li},
  year = {2024},
  eprint = {2407.00782},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2407.00782v3},
}