Using large language models to categorize strategic situations and decipher motivations behind human behaviors

• 成果类型: Article
• 署名作者: Xie, Yutong; Mei, Qiaozhu; Yuan, Walter; Jackson, Matthew O.
• 署名单位: University of Michigan System; University of Michigan; Stanford University; The Santa Fe Institute
• 刊物名称: PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA
• ISSN/ISSBN: 0027-10077
• DOI: 10.1073/pnas.2512075122
• 发表日期: 2025-09-02
• 关键词: Bias

摘要

By varying prompts to a large language model, we can elicit the full range of human behaviors in a variety of different scenarios in classic economic games. By analyzing which prompts elicit which behaviors, we can categorize and compare different strategic situations, which can also help provide insight into what different economic scenarios might induce people to think about. We discuss how this provides a step toward a nonstandard method of inferring (deciphering) the motivations behind the human behaviors. We also show how this deciphering process can be used to categorize differences in the behavioral tendencies of different populations.