@article{exploringpolyglotharmonyonmultilingualda, title = {Exploring Polyglot Harmony: On Multilingual Data Allocation for Large Language Models Pretraining}, author = {Ping Guo and Yubing Ren and Binbin Liu and Fengze Liu and Haobin Lin and Yifan Zhang and Bingni Zhang and Taifeng Wang and Yin Zheng}, year = {2025}, eprint = {2509.15556}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2509.15556}, }