@article{datadecidehowtopredictbestpretraining, title = {DataDecide: How to Predict Best Pretraining Data with Small Experiments}, author = {Ian Magnusson and Nguyen Tai and Ben Bogin and David Heineman and Jena D. Hwang and Luca Soldaini and Akshita Bhagia and Jiacheng Liu and Dirk Groeneveld and Oyvind Tafjord and Noah A. Smith and Pang Wei Koh and Jesse Dodge}, year = {2025}, eprint = {2504.11393}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2504.11393v1}, }