@article{hardnegativesampleaugmenteddpoposttraini, title = {Hard Negative Sample-Augmented DPO Post-Training for Small Language Models}, author = {Haocheng Lu and Minjun Zhu and Henry Yu}, year = {2025}, eprint = {2512.19728}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2512.19728}, }