AI-generated stories favour stability over change: homogeneity and cultural stereotyping in narratives generated by gpt-4o-mini

2025-07-30

AI Summary

This study investigates whether Anglo-American–trained language models can generate genuinely diverse, cross-cultural narratives. Method: Leveraging GPT-4o-mini, we generated 11,800 stories across cultural contexts, applying prompt engineering and cross-cultural narrative analysis to systematically identify structural patterns. Contribution/Results: We find that AI consistently favors stable, nostalgic, conflict-averse linear narratives—underemphasizing transformation, character development, and sociocultural tension—thereby converging on a standardized “community-return” template that homogenizes cultural expression. We introduce “narrative homogenization” as a novel form of AI bias: distinct from representational bias, it arises from the model’s structural preference for tradition and stability, thereby actively suppressing cultural diversity and dynamic evolution. This work establishes a new theoretical framework and empirical benchmark for evaluating large language models’ cultural adaptability.

Technology Category

• Natural Language Processing: (Large) Language Models
• Humans and AI: Game Design — Procedural Content Generation & Storytelling
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• 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

Abstract

Can a language model trained largely on Anglo-American texts generate stories that are culturally relevant to other nationalities? To find out, we generated 11,800 stories - 50 for each of 236 countries - by sending the prompt "Write a 1500 word potential {demonym} story" to OpenAI's model gpt-4o-mini. Although the stories do include surface-level national symbols and themes, they overwhelmingly conform to a single narrative plot structure across countries: a protagonist lives in or returns home to a small town and resolves a minor conflict by reconnecting with tradition and organising community events. Real-world conflicts are sanitised, romance is almost absent, and narrative tension is downplayed in favour of nostalgia and reconciliation. The result is a narrative homogenisation: an AI-generated synthetic imaginary that prioritises stability above change and tradition above growth. We argue that the structural homogeneity of AI-generated narratives constitutes a distinct form of AI bias, a narrative standardisation that should be acknowledged alongside the more familiar representational bias. These findings are relevant to literary studies, narratology, critical AI studies, NLP research, and efforts to improve the cultural alignment of generative AI.

Problem

• AI-generated stories lack cultural diversity and relevance
• Narratives favor stability, tradition over conflict and growth
• Structural homogeneity in AI stories represents a new bias

Innovation

• Generated 11,800 stories for cultural analysis
• Used GPT-4o-mini for narrative homogeneity study
• Identified AI bias in structural narrative patterns