@inproceedings{zhang-etal-2024-intermediate,
    title = "Intermediate Layer Distillation with the Reused Teacher Classifier: A Study on the Importance of the Classifier of Attention-based Models",
    author = "Zhang, Hang  and
      Mozafari, Seyyed Hasan  and
      Clark, James J.  and
      Meyer, Brett H.  and
      Gross, Warren J.",
    editor = "Al-Onaizan, Yaser  and
      Bansal, Mohit  and
      Chen, Yun-Nung",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
    month = nov,
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2024.findings-emnlp.422/",
    doi = "10.18653/v1/2024.findings-emnlp.422",
    pages = "7203--7212"
}