@inproceedings{shi-etal-2026-grail,
    title = "{GRAIL}: Gradient-Reward Aligned Initialization for {L}o{RA}-based {GRPO}",
    author = "Shi, Liwen  and
      Zeng, Zijie  and
      Wang, Bowen  and
      Yunji  and
      Chen, Zeyu  and
      Shao, Xinyu  and
      Sun, Xinzheng  and
      Xiong, Xuyang  and
      Wu, Haoyang  and
      Zhang, Sheng",
    editor = "Lee, Hung-Yi  and
      Dev, Sunipa  and
      Li, Jessy  and
      Elliott, Desmond",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.findings-emnlp.926/",
    pages = "19549--19565",
    ISBN = "979-8-89176-462-0"
}