@article{difficultybasedpreferencedataselectionby, title = {Difficulty-Based Preference Data Selection by DPO Implicit Reward Gap}, author = {Xuan Qi and Rongwu Xu and Zhijing Jin}, year = {2025}, eprint = {2508.04149}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2508.04149}, }