Using Large Language Models to Categorize Strategic Situations and Decipher Motivations Behind Human Behaviors
This provides a non-standard approach for inferring motivations in economic scenarios, which could benefit researchers in behavioral economics and AI, but it appears incremental as it builds on existing LLM capabilities.
The researchers tackled the problem of categorizing strategic situations and inferring motivations behind human behaviors by varying prompts to a large language model in classic economic games, resulting in a method to analyze elicited behaviors and compare scenarios without specifying concrete numerical results.
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 induce people to think about. We discuss how this provides a first step towards a non-standard 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.