@article{wpoenhancingrlhfwithweightedpreference, title = {WPO: Enhancing RLHF with Weighted Preference Optimization}, author = {Wenxuan Zhou and Ravi Agrawal and Shujian Zhang and Sathish Reddy Indurthi and Sanqiang Zhao and Kaiqiang Song and Silei Xu and Chenguang Zhu}, year = {2024}, eprint = {2406.11827}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2406.11827v2}, }