@article{preferenceasrewardmaximumpreference, title = {Preference as Reward, Maximum Preference Optimization with Importance Sampling}, author = {Zaifan Jiang and Xing Huang and Chao Wei}, year = {2023}, eprint = {2312.16430}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2312.16430v5}, }