Identity, Cooperation and Framing Effects within Groups of Real and Simulated Humans

2026-01-22

AI Summary

This work proposes a novel approach to enhance the realism of large language models (LLMs) in simulating human behavior in social dilemma games by explicitly modeling identity-driven actions and context-dependent decision-making. Moving beyond conventional weak role prompts, the method deeply integrates narrative-rich identity profiles with instruction tuning and a consistency verification mechanism to construct a robust social dilemma simulation framework. Experimental results demonstrate that the proposed framework successfully replicates key empirical findings from human studies regarding the influence of identity and contextual factors—such as time pressure, problem framing, and group composition—on strategic choices. This advancement significantly improves the granularity, fidelity, and reproducibility of simulated social behaviors in computational models.

Technology Category

• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Machine Learning: Imitation Learning & Inverse Reinforcement Learning

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Economics, Online Markets and Human Computation: Humans versus LLMs for data annotation and labeling
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Humans act via a nuanced process that depends both on rational deliberation and also on identity and contextual factors. In this work, we study how large language models (LLMs) can simulate human action in the context of social dilemma games. While prior work has focused on"steering"(weak binding) of chat models to simulate personas, we analyze here how deep binding of base models with extended backstories leads to more faithful replication of identity-based behaviors. Our study has these findings: simulation fidelity vs human studies is improved by conditioning base LMs with rich context of narrative identities and checking consistency using instruction-tuned models. We show that LLMs can also model contextual factors such as time (year that a study was performed), question framing, and participant pool effects. LLMs, therefore, allow us to explore the details that affect human studies but which are often omitted from experiment descriptions, and which hamper accurate replication.

Problem

• identity
• cooperation
• framing effects
• social dilemma
• simulation fidelity

Innovation

• deep binding
• large language models
• identity simulation
• social dilemma games
• contextual factors