@article{chen2026learning,
    title={Learning Ordinal Probabilistic Reward from Preferences},
    author={Chen, Longze and Wang, Lu and Shan, Renke and Gong, Ze and Luo, Run and Li, Jiaming and Luo, Jing and Wang, Qiyao and Yang, Min},
    journal={arXiv preprint arXiv:2602.12660},
    year={2026},
    url={https://arxiv.org/abs/2602.12660}
}