@inproceedings{li-etal-2026-cultures,
title = "When Cultures Move: Measuring and Improving Multicultural Text-to-Video Generation",
author = "Li, Shuowei and
Zhao, Yuming and
Bhalerao, Parth and
Ignat, Oana",
editor = "Atwell, Katherine and
Borah, Angana and
Dementieva, Daryna and
Kreiss, Elisa and
Kotonya, Neema and
Liu, Jiarui and
Olson, Liz and
Wan, Ruyuan and
Zhao, Jieyu",
booktitle = "Proceedings of the Fifth Workshop on {NLP} for Positive Impact ({NLP}4{PI})",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.nlp4pi-1.42/",
pages = "575--591",
ISBN = "979-8-89176-495-8",
abstract = "Text-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."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2026-cultures">
<titleInfo>
<title>When Cultures Move: Measuring and Improving Multicultural Text-to-Video Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shuowei</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuming</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Parth</namePart>
<namePart type="family">Bhalerao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Oana</namePart>
<namePart type="family">Ignat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth Workshop on NLP for Positive Impact (NLP4PI)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Katherine</namePart>
<namePart type="family">Atwell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Angana</namePart>
<namePart type="family">Borah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daryna</namePart>
<namePart type="family">Dementieva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elisa</namePart>
<namePart type="family">Kreiss</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Neema</namePart>
<namePart type="family">Kotonya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiarui</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liz</namePart>
<namePart type="family">Olson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruyuan</namePart>
<namePart type="family">Wan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jieyu</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-495-8</identifier>
</relatedItem>
<abstract>Text-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.</abstract>
<identifier type="citekey">li-etal-2026-cultures</identifier>
<location>
<url>https://aclanthology.org/2026.nlp4pi-1.42/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>575</start>
<end>591</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T When Cultures Move: Measuring and Improving Multicultural Text-to-Video Generation
%A Li, Shuowei
%A Zhao, Yuming
%A Bhalerao, Parth
%A Ignat, Oana
%Y Atwell, Katherine
%Y Borah, Angana
%Y Dementieva, Daryna
%Y Kreiss, Elisa
%Y Kotonya, Neema
%Y Liu, Jiarui
%Y Olson, Liz
%Y Wan, Ruyuan
%Y Zhao, Jieyu
%S Proceedings of the Fifth Workshop on NLP for Positive Impact (NLP4PI)
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-495-8
%F li-etal-2026-cultures
%X Text-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.
%U https://aclanthology.org/2026.nlp4pi-1.42/
%P 575-591
Markdown (Informal)
[When Cultures Move: Measuring and Improving Multicultural Text-to-Video Generation](https://aclanthology.org/2026.nlp4pi-1.42/) (Li et al., NLP4PI 2026)
ACL