@article{selftrainingwithdirectpreference,
  title = {Self-Training with Direct Preference Optimization Improves Chain-of-Thought Reasoning},
  author = {Tianduo Wang and Shichen Li and Wei Lu},
  year = {2024},
  eprint = {2407.18248},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2407.18248v1},
}