@article{embeddingdrivendiversitysamplingto, title = {Embedding-Driven Diversity Sampling to Improve Few-Shot Synthetic Data Generation}, author = {Ivan Lopez and Fateme Nateghi Haredasht and Kaitlin Caoili and Jonathan H Chen and Akshay Chaudhari}, year = {2025}, eprint = {2501.11199}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2501.11199v2}, }