@inproceedings{dl3-b-deduplication-training-measure-1,
  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 = {2022},
  url = {https://aclanthology.org/2022.acl-long.577/},
  booktitle = {Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  pages = {8424-8445},
  doi = {10.18653/v1/2022.acl-long.577}
}

@misc{dl3-b-deduplication-training-measure-2,
  title = {Deduplicating Training Data Mitigates Privacy Risks in Language Models},
  author = {Nikhil Kandpal and Eric Wallace and Colin Raffel},
  year = {2022},
  url = {https://arxiv.org/abs/2202.06539},
  howpublished = {arXiv preprint},
  archivePrefix = {arXiv},
  eprint = {2202.06539},
  note = {Cited author-manuscript edition; peer review is not inferred from arXiv}
}

@misc{dl3-b-deduplication-training-measure-3,
  title = {SemDeDup: Data-efficient learning at web-scale through semantic deduplication},
  author = {Amro Abbas and Kushal Tirumala and Dániel Simig and Surya Ganguli and Ari S. Morcos},
  year = {2023},
  url = {https://arxiv.org/abs/2303.09540},
  howpublished = {arXiv preprint},
  archivePrefix = {arXiv},
  eprint = {2303.09540},
  note = {Cited author-manuscript edition; peer review is not inferred from arXiv}
}

@misc{dl3-b-deduplication-training-measure-4,
  title = {DataComp: In search of the next generation of multimodal datasets},
  author = {Samir Yitzhak Gadre and Gabriel Ilharco and Alex Fang and et al.},
  year = {2023},
  url = {https://arxiv.org/abs/2304.14108},
  howpublished = {arXiv preprint},
  archivePrefix = {arXiv},
  eprint = {2304.14108},
  note = {Cited author-manuscript edition; peer review is not inferred from arXiv}
}

@misc{dl3-b-deduplication-training-measure-5,
  title = {Beyond neural scaling laws: beating power law scaling via data pruning},
  author = {Ben Sorscher and Robert Geirhos and Shashank Shekhar and Surya Ganguli and Ari S. Morcos},
  year = {2022},
  url = {https://arxiv.org/abs/2206.14486},
  howpublished = {arXiv preprint},
  archivePrefix = {arXiv},
  eprint = {2206.14486},
  note = {Cited author-manuscript edition; peer review is not inferred from arXiv}
}

@misc{dl3-b-deduplication-training-measure-6,
  title = {Scaling Data-Constrained Language Models},
  author = {Niklas Muennighoff and Alexander M. Rush and Boaz Barak and Teven Le Scao and Aleksandra Piktus and Nouamane Tazi and Sampo Pyysalo and Thomas Wolf and Colin Raffel},
  year = {2023},
  url = {https://arxiv.org/abs/2305.16264},
  howpublished = {arXiv preprint},
  archivePrefix = {arXiv},
  eprint = {2305.16264},
  note = {Cited author-manuscript edition; peer review is not inferred from arXiv}
}