@article{tokenizationimpactsmultilinguallanguage,
  title = {Tokenization Impacts Multilingual Language Modeling: Assessing Vocabulary Allocation and Overlap Across Languages},
  author = {Tomasz Limisiewicz and Jiří Balhar and David Mareček},
  year = {2023},
  eprint = {2305.17179},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2305.17179v1},
}