@inproceedings{yang-etal-2025-selective,
    title = "Selective Preference Optimization via Token-Level Reward Function Estimation",
    author = "Yang, Kailai  and
      Liu, Zhiwei  and
      Xie, Qianqian  and
      Huang, Jimin  and
      Min, Erxue  and
      Ananiadou, Sophia",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-main.359/",
    pages = "7043--7067",
    ISBN = "979-8-89176-332-6"
}