@inproceedings{qiu-etal-2025-demons,
    title = "Demons in the Detail: On Implementing Load Balancing Loss for Training Specialized Mixture-of-Expert Models",
    author = "Qiu, Zihan  and
      Huang, Zeyu  and
      Zheng, Bo  and
      Wen, Kaiyue  and
      Wang, Zekun  and
      Men, Rui  and
      Titov, Ivan  and
      Liu, Dayiheng  and
      Zhou, Jingren  and
      Lin, Junyang",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/acl25-workshop-ingestion/2025.acl-long.249/",
    pages = "5005--5018",
    ISBN = "979-8-89176-251-0"
}