Large Language Models Predict Human Social Behavior via Interpretable Mechanisms
Listed in
This article is not in any list yet, why not save it to one of your lists.Abstract
The development of large language models (LLMs) offers promising opportunities for predicting human behavior across diverse contexts. However, most prior work has emphasized behavioral imitation, with limited attention to transparent or interpretable models of the cognitive mechanisms underlying human decisions. In this study, we introduce MindEvolve, an autonomous workflow designed to predict behavior in social interactions by generating interpretable symbolic models of cognition. We systematically evaluate the modeling capabilities of multiple LLMs across a battery of socioeconomic games covering four core domains of social cognition: economic preferences, social preferences, social reasoning (theory of mind), and recursive planning. The symbolic models proposed by the LLMs are assessed by expert human evaluators for interpretability and theoretical coherence. Our results show that while most LLMs robustly capture economic and social preferences in relatively simple strategic settings—and in some cases generate novel models that integrate broader knowledge than those proposed by human experts—their capacity to model more complex psychological processes remains limited. However, a subset of state-of-the-art models demonstrates promising performance in capturing higher-order reasoning processes such as theory of mind and recursive planning. Together, these findings highlight the emerging potential of LLMs not only to imitate behavior, but to generate interpretable, mechanistic accounts of human social decision-making. Our results provide a roadmap for advancing LLM-based cognitive modeling toward human-expert-level theory construction.
Significance Statement
Large language models can increasingly predict human behavior, but whether they can construct interpretable models of the cognitive mechanisms underlying behavior remains unclear. We introduce MindEvolve, a framework that uses large language models to autonomously build symbolic models of human social decision-making. Across tasks involving economic and social preferences, theory of mind, and repeated trust interactions, these models generated transparent, expert-evaluable cognitive models and sometimes proposed theoretically meaningful strategies beyond existing approaches. Although complex social reasoning and long-horizon planning remain challenging, advanced models already show emerging abilities to capture higher-order cognitive processes. These findings suggest that large language models may become powerful scientific tools for constructing and discovering theories of human cognition.
