@article{selfplaypreferenceoptimizationfor, title = {Self-Play Preference Optimization for Language Model Alignment}, author = {Yue Wu and Zhiqing Sun and Huizhuo Yuan and Kaixuan Ji and Yiming Yang and Quanquan Gu}, year = {2024}, eprint = {2405.00675}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2405.00675v5}, }