Using Language Models to Decipher the Motivation Behind Human Behaviors

2025-03-20

AI Summary

This study aims to decode the latent motivations underlying human economic decision-making and uncover cognitive differences across contexts and populations. Methodologically, it introduces the first systematic application of prompt engineering to motivation inversion: controllable prompts are used to elicit diverse behavioral responses from large language models (LLMs) in canonical economic games, establishing a “behavior–prompt–motivation” mapping framework; motivation structures are then reverse-inferred via cross-contextual semantic analysis. Key contributions are threefold: (1) identification of a quantifiable latent cognitive structure shared across economic games; (2) successful replication and decoding of multiple empirically observed human decision patterns; and (3) quantification of systematic intergroup differences in motivational inclinations. This work establishes the first interpretable and controllable AI-driven research paradigm for behavioral economics.

Technology Category

• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior
• Game Theory and Economic Paradigms: Behavioral Game Theory
• Humans and AI: Learning Human Values and Preferences

Application Category

• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems
• User Modeling, Personalization and Recommendation: Psychology-informed user models and recommender systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

AI presents a novel tool for deciphering the motivations behind human behaviors. We show that by varying prompts to a large language model, we can elicit a full range of human behaviors in a variety of different scenarios in terms of classic economic games. Then by analyzing which prompts are needed to elicit which behaviors, we can infer (decipher) the motivations behind the human behaviors. We also show how one can analyze the prompts to reveal relationships between the classic economic games, providing new insight into what different economic scenarios induce people to think about. We also show how this deciphering process can be used to understand differences in the behavioral tendencies of different populations.

Problem

• Decipher motivations behind human behaviors using AI.
• Analyze prompts to infer human behavior in economic games.
• Understand behavioral differences across diverse populations.

Innovation

• Varying prompts to elicit human behaviors
• Analyzing prompts to infer behavioral motivations
• Understanding population differences via prompt analysis