Reinforcement Learning to Train Large Language Models to Explain Human Decisions
a year ago
- #Cognitive Modeling
- #Reinforcement Learning
- #Artificial Intelligence
- 探索利用强化学习训练大型语言模型（LLMs）来解释人类决策
- 旨在开发兼具预测功能与可解释性的双重认知模型
- 通过基于结果的奖励机制生成人类风险决策的显式推理轨迹
- 实验表明该方法能高质量解释人类决策并实现强量化预测