@misc{indiciae3cdedcfe4435,
  title = {Guided tokenization and domain knowledge enhance genomic language models' performance},
  author = {Mahangade, V. and Mollerus, M. and Crandall, K. A. and Rahnavard, A.},
  year = {2026},
  doi = {10.64898/2026.02.16.706213},
  url = {https://www.biorxiv.org/content/10.64898/2026.02.16.706213v1},
  note = {Source identifier: 10.64898/2026.02.16.706213}
}