@inproceedings{shen-etal-2025-autoclean, title = "{A}uto{C}lean: {LLM}s Can Prepare Their Training Corpus", author = "Shen, Xingyu and Hu, Shengding and Zhang, Xinrong and Han, Xu and Meng, Xiaojun and Wei, Jiansheng and Liu, Zhiyuan and Sun, Maosong", editor = "Dziri, Nouha and Ren, Sean (Xiang) and Diao, Shizhe", booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (System Demonstrations)", month = apr, year = "2025", address = "Albuquerque, New Mexico", publisher = "Association for Computational Linguistics", url = "https://preview.aclanthology.org/fix-sig-urls/2025.naacl-demo.9/", pages = "85--95", ISBN = "979-8-89176-191-9" }