@inproceedings{yam-paek-2024-baby, title = "What should Baby Models read? Exploring Sample-Efficient Data Composition on Model Performance", author = "Yam, Hong Meng and Paek, Nathan", editor = "Hu, Michael Y. and Mueller, Aaron and Ross, Candace and Williams, Adina and Linzen, Tal and Zhuang, Chengxu and Choshen, Leshem and Cotterell, Ryan and Warstadt, Alex and Wilcox, Ethan Gotlieb", booktitle = "The 2nd BabyLM Challenge at the 28th Conference on Computational Natural Language Learning", month = nov, year = "2024", address = "Miami, FL, USA", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/2024.conll-babylm.25/", pages = "284--291" }