Cross-Cultural Simulation of Citizen Emotional Responses to Bureaucratic Red Tape Using LLM Agents

2026-04-14

AI Summary

This study addresses the lack of empirical validation in current large language models’ ability to simulate citizens’ emotional responses to bureaucratic red tape across diverse cultural contexts. To bridge this gap, the authors propose the first cross-cultural evaluation framework for emotional reactions, integrating culturally tailored prompting strategies with RAMO—an interactive simulation platform. Through empirical comparison between model-generated outputs and real human responses, the research reveals that existing models exhibit limited alignment with human affective patterns overall, with notably weaker performance in Eastern cultural settings. Moreover, the culturally informed prompting strategy demonstrates negligible effectiveness. The authors publicly release the RAMO platform to support future research in multicultural human–AI interaction, offering both a novel tool and a benchmark for evaluating culturally grounded affective modeling.

Technology Category

• Cognitive Modeling & Cognitive Systems: Affective Computing
• Humans and AI: Emotional Intelligence
• Natural Language Processing: (Large) Language Models

Application Category

• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems

Abstract

Improving policymaking is a central concern in public administration. Prior human subject studies reveal substantial cross-cultural differences in citizens' emotional responses to red tape during policy implementation. While LLM agents offer opportunities to simulate human-like responses and reduce experimental costs, their ability to generate culturally appropriate emotional responses to red tape remains unverified. To address this gap, we propose an evaluation framework for assessing LLMs' emotional responses to red tape across diverse cultural contexts. As a pilot study, we apply this framework to a single red-tape scenario. Our results show that all models exhibit limited alignment with human emotional responses, with notably weaker performance in Eastern cultures. Cultural prompting strategies prove largely ineffective in improving alignment. We further introduce \textbf{RAMO}, an interactive interface for simulating citizens' emotional responses to red tape and for collecting human data to improve models. The interface is publicly available at https://ramo-chi.ivia.ch.

Problem

• cross-cultural
• emotional responses
• red tape
• LLM agents
• public administration

Innovation

• LLM agents
• cross-cultural simulation
• emotional response
• red tape
• RAMO interface