@article{whenlessismoreinvestigatingdatapruning,
  title = {When Less is More: Investigating Data Pruning for Pretraining LLMs at Scale},
  author = {Max Marion and Ahmet Üstün and Luiza Pozzobon and Alex Wang and Marzieh Fadaee and Sara Hooker},
  year = {2023},
  eprint = {2309.04564},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2309.04564v1},
}