LAMDA: Large Language Model as Decision Analyst

研究简介

LAMDA 利用大语言模型，将决策问题的非结构化自然语言描述转化为影响图初稿。该框架结合图结构生成与概率获取，通过基于规则的校验和迭代重新生成，修正结构与格式问题。研究在典型风险决策问题数据集上开展评估，并将 LAMDA 应用于专家围绕假想疫情开展的小组讨论。生成的影响图组织了与决策相关的变量、关系、信念和偏好，供人工审查与完善，从而辅助决策分析师进行信息处理和决策分析。

引用格式

HONG Y, QIN S Z, WANG C. LAMDA: Large Language Model as Decision Analyst[J/OL]. Decision Analysis, 2026, Articles in Advance. https://doi.org/10.1287/deca.2025.0438.

BibTeX

@article{Qin20260807LAMDA,
  title = {LAMDA: Large Language Model as Decision Analyst},
  author = {Hong, Yifan and Qin, Sizhong and Wang, Chen},
  year = {2026},
  doi = {10.1287/deca.2025.0438},
  journal = {Decision Analysis}
}