@inproceedings{yang-etal-2026-consistency,
    title = "Consistency-Calibrated Advantage Estimation for Label-Free Reinforcement Learning",
    author = "Yang, Meng  and
      Zhao, Yongle  and
      Zhang, Zhiyang  and
      Jiang, Xiaorui  and
      Liang, Peirou  and
      Chen, Furui  and
      Xie, Yin  and
      Feng, Ziyong",
    editor = "Lee, Hung-Yi  and
      Dev, Sunipa  and
      Li, Jessy  and
      Elliott, Desmond",
    booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.emnlp-main.2484/",
    pages = "56413--56425",
    ISBN = "979-8-89176-459-0"
}