@article{sppdselftrainingwithprocesspreference, title = {SPPD: Self-training with Process Preference Learning Using Dynamic Value Margin}, author = {Hao Yi and Qingyang Li and Yulan Hu and Fuzheng Zhang and Di Zhang and Yong liu}, year = {2025}, eprint = {2502.13516}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2502.13516v1}, }