@article{explainablereinforcementlearningfromhuma,
  title = {Explainable reinforcement learning from human feedback to improve alignment},
  author = {Shicheng Liu and Siyuan Xu and Wenjie Qiu and Hangfan Zhang and Minghui Zhu},
  year = {2025},
  eprint = {2512.13837},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2512.13837},
}