@article{improvingpretrainingdatausingperplexity,
  title = {Improving Pretraining Data Using Perplexity Correlations},
  author = {Tristan Thrush and Christopher Potts and Tatsunori Hashimoto},
  year = {2024},
  eprint = {2409.05816},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2409.05816v1},
}