@inproceedings{lv-etal-2026-mitigating,
    title = "Mitigating False Credit Propagation: Probabilistic Graphical Reward Aggregation for Rubric-Based Reinforcement Learning",
    author = "Lv, Can  and
      Chen, Mingju  and
      Chang, Heng  and
      Zhou, Shiji",
    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.1933/",
    pages = "43980--44003",
    ISBN = "979-8-89176-459-0"
}