@inproceedings{wu-etal-2026-data, title = "The Data Frontier for Large Language Models: Selection, Synthesis, and Tools", author = "Wu, Lijun and Zhang, Wentao and He, Conghui", editor = "Andreas, Jacob and Murray, Kenton", booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 5: Tutorial Abstracts)", month = jul, year = "2026", address = "San Diego, California, USA", publisher = "Association for Computational Linguistics", url = "https://preview.aclanthology.org/ingest-acl/2026.acl-1.2/", pages = "3--4", ISBN = "979-8-89176-394-4" }