@article{thetokenizationbottleneckhowvocabularyex,
  title = {The Tokenization Bottleneck: How Vocabulary Extension Improves Chemistry Representation Learning in Pretrained Language Models},
  author = {Prathamesh Kalamkar and Ned Letcher and Meissane Chami and Sahger Lad and Shayan Mohanty and Prasanna Pendse},
  year = {2025},
  eprint = {2511.14365},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2511.14365},
}