@article{unpackingtokenizationevaluatingtext,
  title = {Unpacking Tokenization: Evaluating Text Compression and its Correlation with Model Performance},
  author = {Omer Goldman and Avi Caciularu and Matan Eyal and Kris Cao and Idan Szpektor and Reut Tsarfaty},
  year = {2024},
  eprint = {2403.06265},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2403.06265v2},
}