@article{diversitymeasurementandsubsetselection, title = {Diversity Measurement and Subset Selection for Instruction Tuning Datasets}, author = {Peiqi Wang and Yikang Shen and Zhen Guo and Matthew Stallone and Yoon Kim and Polina Golland and Rameswar Panda}, year = {2024}, eprint = {2402.02318}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2402.02318v1}, }