@article{beyondlengthquantifyinglongrangeinformat, title = {Beyond Length: Quantifying Long-Range Information for Long-Context LLM Pretraining Data}, author = {Haoran Deng and Yingyu Lin and Zhenghao Lin and Xiao Liu and Yizhou Sun and Yi-An Ma and Yeyun Gong}, year = {2025}, eprint = {2510.25804}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2510.25804}, }