@article{theroleofmixedlanguagedocumentsformultil, title = {The Role of Mixed-Language Documents for Multilingual Large Language Model Pretraining}, author = {Jiandong Shao and Raphael Tang and Crystina Zhang and Karin Sevegnani and Pontus Stenetorp and Jianfei Yang and Yao Lu}, year = {2026}, eprint = {2601.00364}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2601.00364}, }