@misc{wang2022what,
  title={What Language Model Architecture and Pretraining Objective Work Best for Zero-Shot Generalization?},
  author={Thomas Wang and Adam Roberts and Daniel Hesslow and Teven Le Scao and Hyung Won Chung and Iz Beltagy and Julien Launay and Colin Raffel},
  year={2022},
  eprint={2204.05832},
  archivePrefix={arXiv},
  primaryClass={cs.CL},
  url={https://arxiv.org/abs/2204.05832}
}