@article{easydatasetaunifiedandextensibleframewor, title = {Easy Dataset: A Unified and Extensible Framework for Synthesizing LLM Fine-Tuning Data from Unstructured Documents}, author = {Ziyang Miao and Qiyu Sun and Jingyuan Wang and Yuchen Gong and Yaowei Zheng and Shiqi Li and Richong Zhang}, year = {2025}, eprint = {2507.04009}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2507.04009}, }