@article{towardsactivesyntheticdatagenerationforf, title = {Towards Active Synthetic Data Generation for Finetuning Language Models}, author = {Samuel Kessler and Menglin Xia and Daniel Madrigal Diaz and Dongge Han and Helia Heshemi and Saravan Rajmohan and Victor Ruehle and Jordan T. Ash}, year = {2025}, eprint = {2512.00884}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2512.00884}, }