Toward Cultural Alignment: Human-Centered Evaluation of Multimodal AI Stories Across Five African Communities

2026-08-29

AI Summary

本文通过结合定量标注和定性讨论的方法，评估AI生成的多模态故事与五个非洲社区文化的一致性，并提出一种文化一致性的分类方法。

Abstract

In this paper, we examine how well AI-generated multimodal stories align with the lived practices, relationships, language, values, and visual expectations of the communities they represent. We conduct a community-grounded mixed-methods evaluation with 19 culture representatives across five African communities, combining quantitative annotations with qualitative focus group discussions. We find that cultural alignment depends not simply on recognizable cultural markers, but on how those markers fit social, linguistic, procedural, and visual context. From these evaluations, we develop a taxonomy of cultural alignment comprising five broader cultural marker categories and eight recurring mechanisms of misalignment. We additionally evaluate five multimodal LLM judges to examine whether automated evaluation can approximate community-grounded judgments at scale. Judge reliability and score calibration vary substantially across communities, with no single judge performing consistently across all five settings. These findings motivate community-calibrated evaluation pipelines in which automated judges are validated against community judgments to determine where they can be trusted and where human review remains necessary.

Problem

• Cultural Alignment
• Multimodal AI Stories
• African Communities
• Community-Grounded Evaluation

Innovation

• cultural alignment
• multimodal AI stories
• community-grounded evaluation
• automated judges
• mixed-methods