paper
Characterizing Cultural Localization in AI-Generated Stories
paperactiveprovisional
characterizing-cultural-localization-in-ai-generated-stories-a0ec4fa4·1 events·first seen 2d agoAliases: Characterizing Cultural Localization in AI-Generated Stories
More like this (12)
Beyond Accuracy: Community Perspectives on Machine Translationanthropomorphism in AIAgentic AI SystemsData Journalist Agent: Transforming Data into Verifiable Multimodal StoriesAdversarial Creation and Detection of AI-Generated Social Bot ContentUnintended Effects of Geographic Conditioning in Large Language Modelspersonalized AI agentsProvenance Tracking in AI Compilers through the Lens of CoalgebraRetell AIThe Masked Advantage: Uncovering Local-Language Access to Cultural Knowledge in LLMsArtificial Analysis Conversational DynamicsReasoning over Grammar: Can Synthetic Linguistic Reasoning Traces Enhance Low-Resource Machine Translation?
Recent events (1)
Study finds AI-generated stories rely on superficial cultural markers rather than holistic localization
Researchers propose a method to measure the degree of 'templated' versus 'holistic' cultural localization in AI-generated stories, finding that only 9-17% of vocabulary accounts for cross-national variation and that a shared culturally-agnostic narrative template underlies most outputs. The study evaluates five models across 125 topics and 193 nationalities. A notable finding is that cultural markers associated with 19 countries—mostly in the Global South—are rated as offensive on average, raising concerns about bias and representation in multilingual/multicultural AI content generation.