@inproceedings{iyer-2024-babies,
    title = "When Babies Teach Babies: Can student knowledge sharing outperform Teacher-Guided Distillation on small datasets?",
    author = "Iyer, Srikrishna",
    editor = "Hu, Michael Y.  and
      Mueller, Aaron  and
      Ross, Candace  and
      Williams, Adina  and
      Linzen, Tal  and
      Zhuang, Chengxu  and
      Choshen, Leshem  and
      Cotterell, Ryan  and
      Warstadt, Alex  and
      Wilcox, Ethan Gotlieb",
    booktitle = "The 2nd BabyLM Challenge at the 28th Conference on Computational Natural Language Learning",
    month = nov,
    year = "2024",
    address = "Miami, FL, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2024.conll-babylm.17/",
    pages = "197--211",
    abstract = "We present our submission to the BabyLM challenge, aiming to push the boundaries of data-efficient language model pretraining. Our method builds upon deep mutual learning, introducing a student model search for diverse initialization. We address the limitation of treating students equally by formulating weighted mutual learning as a bi-level optimization problem. The inner loop learns compact students through online distillation, while the outer loop optimizes weights for better knowledge distillation from diverse students. This dynamic weighting strategy eliminates the need for a teacher model, reducing computational requirements. Our evaluations show that teacher-less methods can match or surpass teacher-supervised approaches."
}