@article{usingreinforcementlearningtotrainlarge,
  title = {Using Reinforcement Learning to Train Large Language Models to Explain Human Decisions},
  author = {Jian-Qiao Zhu and Hanbo Xie and Dilip Arumugam and Robert C. Wilson and Thomas L. Griffiths},
  year = {2025},
  eprint = {2505.11614},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2505.11614v1},
}