@misc{zhang2023towards,
  title={Towards the Law of Capacity Gap in Distilling Language Models},
  author={Chen Zhang and Dawei Song and Zheyu Ye and Yan Gao},
  year={2023},
  eprint={2311.07052},
  archivePrefix={arXiv},
  primaryClass={cs.CL},
  url={https://arxiv.org/abs/2311.07052}
}