@article{sun-etal-2026-data, title = "Data Foundations of Long-Context Language Models: A Survey", author = "Sun, Zechen and Sun, Yuyang and Su, Zhaochen and Tang, Zecheng and Li, Juntao and Zhou, Ao and Chen, Wenliang and Zhang, Min", journal = "Transactions of the Association for Computational Linguistics", volume = "14", year = "2026", address = "Cambridge, MA", publisher = "MIT Press", url = "https://aclanthology.org/2026.tacl-1.81/", doi = "10.1162/tacl.a.775", pages = "1803--1825" }