@article{revisitingmultilingualdatamixturesinlang, title = {Revisiting Multilingual Data Mixtures in Language Model Pretraining}, author = {Negar Foroutan and Paul Teiletche and Ayush Kumar Tarun and Antoine Bosselut}, year = {2025}, eprint = {2510.25947}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2510.25947}, }