@article{traininglanguagemodelswithhomotokenslead, title = {Training Language Models with homotokens Leads to Delayed Overfitting}, author = {Adrian Cosma and Stefan Ruseti and Emilian Radoi and Mihai Dascalu}, year = {2026}, eprint = {2601.02867}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2601.02867}, }