Characterizing Cultural Localization in AI-Generated Stories

2026-06-12

AI Summary

This study investigates the authenticity of cultural localization in AI-generated narratives, distinguishing between templated and holistic approaches. Through lexical distinctiveness analysis, multi-word sequence detection, and text similarity computation, the authors find that only 9–17% of vocabulary meaningfully differentiates national contexts, while the remainder exhibits high narrative convergence, revealing a shared, culturally neutral storytelling template. Further semantic evaluation demonstrates that cultural markers associated with 19 countries—predominantly from the Global South—are, on average, perceived as offensive. This work presents the first quantitative estimation of the prevalence of templated localization in AI-generated stories and introduces a novel methodology for assessing cultural representational bias in machine-generated narratives.

Abstract

The global use of artificial intelligence has increased interest in assessing the ability to generate culturally localized content, including stories. Cultural localization in stories often occurs through either templated localization -- the use of cultural markers (e.g., names, locations) in a generic narrative -- or holistic localization -- the variation of plots, values, and themes, in addition to cultural markers. We propose a method to measure the degree to which content was generated through templated localization. Specifically, we identify the lexical tokens that distinguish stories across nationalities and measure the similarity of the narratives that remain after removing them. In stories generated by five models on 125 topics for 193 nationalities, our method is able to detect that only a small subset (9-17%) of the vocabulary accounts for the variation across nationalities and that the narratives that remain after removing them contain repeated multi-word sequences, suggesting the presence of a shared culturally-agnostic narrative template. Finally, we characterize the cultural markers for their stereotypicality and offensiveness, finding that markers from 19 countries, mostly located in the Global South, are on average offensive.

Problem

• cultural localization
• AI-generated stories
• templated localization
• cultural markers
• narrative similarity

Innovation

• cultural localization
• templated localization
• narrative similarity
• lexical markers
• AI-generated stories