@inproceedings{wang-etal-2024-self-training,
    title = "Self-Training with Direct Preference Optimization Improves Chain-of-Thought Reasoning",
    author = "Wang, Tianduo  and
      Li, Shichen  and
      Lu, Wei",
    editor = "Ku, Lun-Wei  and
      Martins, Andre  and
      Srikumar, Vivek",
    booktitle = "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = aug,
    year = "2024",
    address = "Bangkok, Thailand",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/Author-page-Marten-During-lu/2024.acl-long.643/",
    doi = "10.18653/v1/2024.acl-long.643",
    pages = "11917--11928"
}