@article{bpegetspickyefficientvocabulary,
  title = {BPE Gets Picky: Efficient Vocabulary Refinement During Tokenizer Training},
  author = {Pavel Chizhov and Catherine Arnett and Elizaveta Korotkova and Ivan P. Yamshchikov},
  year = {2024},
  eprint = {2409.04599},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2409.04599v1},
}