@inproceedings{jin-etal-2025-align,
    title = "Align Attention Heads Before Merging Them: An Effective Way for Converting {MHA} to {GQA}",
    author = "Jin, Qingyun  and
      Song, Xiaohui  and
      Zhou, Feng  and
      Qin, Zengchang",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2025.findings-emnlp.467/",
    pages = "8804--8816",
    ISBN = "979-8-89176-335-7"
}