@article{aratokenoptimizingarabictokenizationwith, title = {AraToken: Optimizing Arabic Tokenization with Normalization Pipeline and Language Extension for Qwen3}, author = {Mark Kashirskiy and Artiom Lipinski and Ilya Makarov}, year = {2025}, eprint = {2512.18399}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2512.18399}, }