@article{beyondscalethediversitycoefficientasa, title = {Beyond Scale: The Diversity Coefficient as a Data Quality Metric for Variability in Natural Language Data}, author = {Brando Miranda and Alycia Lee and Sudharsan Sundar and Allison Casasola and Sanmi Koyejo}, year = {2023}, eprint = {2306.13840}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2306.13840v3}, }