@inproceedings{tampier-etal-2025-recombitext, title = "{R}ecombi{T}ext: Compositional Data Augmentation for Enhancing {LLM} Pre-Training Datasets in Low-Resource Scenarios", author = "Tampier, Alexander and Thoma, Lukas and Schoenegger, Loris and Roth, Benjamin", editor = "Charpentier, Lucas and Choshen, Leshem and Cotterell, Ryan and Gul, Mustafa Omer and Hu, Michael Y. and Liu, Jing and Jumelet, Jaap and Linzen, Tal and Mueller, Aaron and Ross, Candace and Shah, Raj Sanjay and Warstadt, Alex and Wilcox, Ethan Gotlieb and Williams, Adina", booktitle = "Proceedings of the First BabyLM Workshop", month = nov, year = "2025", address = "Suzhou, China", publisher = "Association for Computational Linguistics", url = "https://preview.aclanthology.org/ingest-emnlp/2025.babylm-main.40/", pages = "548--565", ISBN = "TODO" }