@inproceedings{chen-etal-2025-mig, title = "{MIG}: Automatic Data Selection for Instruction Tuning by Maximizing Information Gain in Semantic Space", author = "Chen, Yicheng and Li, Yining and Hu, Kai and Zerun, Ma and HaochenYe, HaochenYe and Chen, Kai", editor = "Che, Wanxiang and Nabende, Joyce and Shutova, Ekaterina and Pilehvar, Mohammad Taher", booktitle = "Findings of the Association for Computational Linguistics: ACL 2025", month = jul, year = "2025", address = "Vienna, Austria", publisher = "Association for Computational Linguistics", url = "https://preview.aclanthology.org/landing_page/2025.findings-acl.515/", pages = "9902--9915", ISBN = "979-8-89176-256-5" }