@article{fromenglishcentrictoeffectivebilingual, title = {From English-Centric to Effective Bilingual: LLMs with Custom Tokenizers for Underrepresented Languages}, author = {Artur Kiulian and Anton Polishko and Mykola Khandoga and Yevhen Kostiuk and Guillermo Gabrielli and Łukasz Gagała and Fadi Zaraket and Qusai Abu Obaida and Hrishikesh Garud and Wendy Wing Yee Mak and Dmytro Chaplynskyi and Selma Belhadj Amor and Grigol Peradze}, year = {2024}, eprint = {2410.18836}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2410.18836v1}, }