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