@article{perplexedbyperplexityperplexitybaseddata, title = {Perplexed by Perplexity: Perplexity-Based Data Pruning With Small Reference Models}, author = {Zachary Ankner and Cody Blakeney and Kartik Sreenivasan and Max Marion and Matthew L. Leavitt and Mansheej Paul}, year = {2024}, eprint = {2405.20541}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2405.20541v1}, }