@article{diversitydrivendataselectionforlanguage, title = {Diversity-driven Data Selection for Language Model Tuning through Sparse Autoencoder}, author = {Xianjun Yang and Shaoliang Nie and Lijuan Liu and Suchin Gururangan and Ujjwal Karn and Rui Hou and Madian Khabsa and Yuning Mao}, year = {2025}, eprint = {2502.14050}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2502.14050v2}, }