@inproceedings{bhalerao-etal-2026-cultures,
title = "When Cultures Meet: Multicultural Text-to-Image Generation",
author = "Bhalerao, Parth and
Ignat, Oana and
Trinh, Brian and
Yalamarty, Mounika",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-acl.1783/",
doi = "10.18653/v1/2026.findings-acl.1783",
pages = "35808--35828",
ISBN = "979-8-89176-395-1",
abstract = "Text-to-image generation models have achieved strong performance in culturally homogeneous settings, yet their ability to generate multicultural scenes{---}where people and landmarks originate from different cultures{---}remains largely unexplored. We introduce multicultural text-to-image generation as a new task and present the first benchmark designed to study this setting. Our dataset contains 9,000 images spanning five countries, three age groups, two genders, 25 historical landmarks, and five languages. Using this benchmark, we analyze the behavior of state-of-the-art text-to-image models across multiple dimensions, including alignment, image quality, aesthetics, knowledge, and fairness. As one strategy for composing cultural and demographic information, we explore MosAIG, a Multi-Agent framework that enhances multicultural image generation by leveraging large language models with distinct cultural personas. Our analysis shows that richer prompt composition can improve image quality and cultural grounding compared to simple prompts, while also revealing substantial disparities across languages and demographic groups. We release our dataset and code at https://github.com/AIM-SCU/MosAIG"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bhalerao-etal-2026-cultures">
<titleInfo>
<title>When Cultures Meet: Multicultural Text-to-Image Generation</title>
</titleInfo>
<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>
<name type="personal">
<namePart type="given">Brian</namePart>
<namePart type="family">Trinh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mounika</namePart>
<namePart type="family">Yalamarty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-395-1</identifier>
</relatedItem>
<abstract>Text-to-image generation models have achieved strong performance in culturally homogeneous settings, yet their ability to generate multicultural scenes—where people and landmarks originate from different cultures—remains largely unexplored. We introduce multicultural text-to-image generation as a new task and present the first benchmark designed to study this setting. Our dataset contains 9,000 images spanning five countries, three age groups, two genders, 25 historical landmarks, and five languages. Using this benchmark, we analyze the behavior of state-of-the-art text-to-image models across multiple dimensions, including alignment, image quality, aesthetics, knowledge, and fairness. As one strategy for composing cultural and demographic information, we explore MosAIG, a Multi-Agent framework that enhances multicultural image generation by leveraging large language models with distinct cultural personas. Our analysis shows that richer prompt composition can improve image quality and cultural grounding compared to simple prompts, while also revealing substantial disparities across languages and demographic groups. We release our dataset and code at https://github.com/AIM-SCU/MosAIG</abstract>
<identifier type="citekey">bhalerao-etal-2026-cultures</identifier>
<identifier type="doi">10.18653/v1/2026.findings-acl.1783</identifier>
<location>
<url>https://aclanthology.org/2026.findings-acl.1783/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>35808</start>
<end>35828</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T When Cultures Meet: Multicultural Text-to-Image Generation
%A Bhalerao, Parth
%A Ignat, Oana
%A Trinh, Brian
%A Yalamarty, Mounika
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Findings of the Association for Computational Linguistics: ACL 2026
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-395-1
%F bhalerao-etal-2026-cultures
%X Text-to-image generation models have achieved strong performance in culturally homogeneous settings, yet their ability to generate multicultural scenes—where people and landmarks originate from different cultures—remains largely unexplored. We introduce multicultural text-to-image generation as a new task and present the first benchmark designed to study this setting. Our dataset contains 9,000 images spanning five countries, three age groups, two genders, 25 historical landmarks, and five languages. Using this benchmark, we analyze the behavior of state-of-the-art text-to-image models across multiple dimensions, including alignment, image quality, aesthetics, knowledge, and fairness. As one strategy for composing cultural and demographic information, we explore MosAIG, a Multi-Agent framework that enhances multicultural image generation by leveraging large language models with distinct cultural personas. Our analysis shows that richer prompt composition can improve image quality and cultural grounding compared to simple prompts, while also revealing substantial disparities across languages and demographic groups. We release our dataset and code at https://github.com/AIM-SCU/MosAIG
%R 10.18653/v1/2026.findings-acl.1783
%U https://aclanthology.org/2026.findings-acl.1783/
%U https://doi.org/10.18653/v1/2026.findings-acl.1783
%P 35808-35828
Markdown (Informal)
[When Cultures Meet: Multicultural Text-to-Image Generation](https://aclanthology.org/2026.findings-acl.1783/) (Bhalerao et al., Findings 2026)
ACL
- Parth Bhalerao, Oana Ignat, Brian Trinh, and Mounika Yalamarty. 2026. When Cultures Meet: Multicultural Text-to-Image Generation. In Findings of the Association for Computational Linguistics: ACL 2026, pages 35808–35828, San Diego, California, United States. Association for Computational Linguistics.