@misc{lee2021deduplicating,
  title={Deduplicating Training Data Makes Language Models Better},
  author={Katherine Lee and Daphne Ippolito and Andrew Nystrom and Chiyuan Zhang and Douglas Eck and Chris Callison-Burch and Nicholas Carlini},
  year={2021},
  eprint={2107.06499},
  archivePrefix={arXiv},
  primaryClass={cs.CL},
  url={https://arxiv.org/abs/2107.06499}
}