Teaching Values to Machines: Simulating Human-Like Behavior in LLMs

2026-05-28

AI Summary

This study addresses the challenge of aligning large language models (LLMs) with human values beyond superficial linguistic mimicry by systematically integrating empirically grounded psychological value frameworks—such as Schwartz’s theory of basic human values—into LLM prompting. The authors introduce value-guided prompts to elicit latent, human-like value structures within LLMs and analyze model behavior through large-scale prompt engineering, value distribution modeling, and cross-model behavioral comparisons. Drawing on over five million question-answer interactions, the research demonstrates that value-guided LLMs exhibit value-behavior coherence closely aligned with human patterns at the population level, significantly enhancing the fidelity of human behavioral simulation. These findings validate value-aligned LLMs as effective high-fidelity proxies for modeling human decision-making and social behavior.

Abstract

Large Language Models (LLMs) demonstrate a remarkable capacity to adopt different personas and roles; however, it remains unclear whether they can manifest behavior that adheres to a coherent, human-like value structure. In this work, we draw on established psychological value theory to induce human-like values in LLMs and assess their alignment with patterns observed in human studies. Using validated psychological questionnaires, we conduct large-scale experiments -- over 5 million questions -- to evaluate value structures and value-behavior relationships in leading LLMs and compare them to humans. Our findings reveal strong agreement between value-prompted LLMs and humans across both dimensions. Moreover, incorporating human value distributions enhances population-level simulations with value-induced LLMs. These findings highlight the potential of value-induced LLMs as effective, psychologically grounded tools for simulating human behavior.

Problem

• Large Language Models
• Human Values
• Value Alignment
• Behavior Simulation
• Psychological Value Theory

Innovation

• value-induced LLMs
• psychological value theory
• human-like behavior simulation
• value-behavior alignment
• large-scale questionnaire evaluation