@article{spomultidimensionalpreferencesequential, title = {SPO: Multi-Dimensional Preference Sequential Alignment With Implicit Reward Modeling}, author = {Xingzhou Lou and Junge Zhang and Jian Xie and Lifeng Liu and Dong Yan and Kaiqi Huang}, year = {2024}, eprint = {2405.12739}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2405.12739v2}, }