@article{distillingstepbystepoutperforminglarger,
  title = {Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes},
  author = {Cheng-Yu Hsieh and Chun-Liang Li and Chih-Kuan Yeh and Hootan Nakhost and Yasuhisa Fujii and Alexander Ratner and Ranjay Krishna and Chen-Yu Lee and Tomas Pfister},
  year = {2023},
  eprint = {2305.02301},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2305.02301v2},
}