@inproceedings{xu-etal-2025-full,
    title = "Full-Step-{DPO}: Self-Supervised Preference Optimization with Step-wise Rewards for Mathematical Reasoning",
    author = "Xu, Huimin  and
      Mao, Xin  and
      Li, Feng-Lin  and
      Wu, Xiaobao  and
      Chen, Wang  and
      Zhang, Wei  and
      Luu, Anh Tuan",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/landing_page/2025.findings-acl.1249/",
    pages = "24343--24356",
    ISBN = "979-8-89176-256-5"
}