Scalable Data Ablation Approximations for Language Models through Modular Training and Merging 2024 inproceedings na2024modulartraining Authors Na, Clara and Magnusson, Ian and Jha, Ananya Harsh and Sherborne, Tom and Strubell, Emma and Dodge, Jesse and Dasigi, Pradeep Venue EMNLP URL https://arxiv.org/abs/2410.15661