@inproceedings{tong-etal-2026-selecting, title = "{SELEC}ting over Tokens: Curating Pre-training Data at Scale via Token Classification", author = "Tong, Xin and Zhang, Weidong and Li, Jiaang and Chen, Haibin and Liu, Shilei and Liu, Langming and Lv, Kangtao and Yuan, Yujin and Su, Wenbo and Zheng, Bo", editor = "Liakata, Maria and Moreira, Viviane P. and Zhang, Jiajun and Jurgens, David", booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)", month = jul, year = "2026", address = "San Diego, California, United States", publisher = "Association for Computational Linguistics", url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.2219/", pages = "48060--48085", ISBN = "979-8-89176-390-6" }