@article{srmirshadowrewardmodelsbasedon,
  title = {HAIR: Hardness-Aware Inverse Reinforcement Learning with Introspective Reasoning for LLM Alignment},
  author = {Ruoxi Cheng and Haoxuan Ma and Weixin Wang},
  year = {2025},
  eprint = {2503.18991},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2503.18991v2},
}