Skip to content
conftrace_
2026 EMNLP EMNLP 2026

When Cultures Move: Measuring and Improving Multicultural Text-to-Video Generation

AbstractText-to-video (T2V) generation has achieved strong visual fidelity, yet its ability to represent multiple cultures within a single scene remains largely unexplored, a gap with real consequences as generative video becomes a mainstream medium for cultural storytelling. We introduce multicultural text-to-video generation as a new task and present the first benchmark designed to study this setting: 243 culturally grounded prompts and 972 videos, spanning three cultures (Chinese, American, Romanian), three action categories, and both mono-cultural and cross-cultural scenarios. Using this benchmark, we analyze how current T2V models represent culture with CLIP-based metrics, VLM-as-judge assessments, and video quality measures. As one strategy for improving cultural fidelity, we explore MAVEN, which decomposes prompts into person, action, and location dimensions, each handled by a culturally specialized agent in parallel or sequentially. In our controlled setting, parallel specialization achieves the strongest cultural relevance while maintaining visual quality and temporal consistency, suggesting that structured prompt refinement is a promising direction for multicultural T2V generation. We release our dataset and code at: https://github.com/AIM-SCU/MAVEN.

More from EMNLP 2026

All EMNLP 2026 papers →