@article{mpomultilingualsafetyalignmentviareward,
  title = {MPO: Multilingual Safety Alignment via Reward Gap Optimization},
  author = {Weixiang Zhao and Yulin Hu and Yang Deng and Tongtong Wu and Wenxuan Zhang and Jiahe Guo and An Zhang and Yanyan Zhao and Bing Qin and Tat-Seng Chua and Ting Liu},
  year = {2025},
  eprint = {2505.16869},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2505.16869v1},
}