@inproceedings{deng-etal-2026-beyond-static,
title = "Beyond Static Symbols: Evidence-Grounded Visual Checklists for Cultural Activity Generation",
author = "Deng, Hongcan and
Ma, Bo and
Yang, Yating and
Ma, Rong and
Wang, Zhen and
Zhou, Xi and
Dong, Rui and
Osman, Turghun",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-main.663/",
pages = "15267--15294",
ISBN = "979-8-89176-459-0",
abstract = "Text-to-image models can render recognizable cultural symbols, but cultural activity generation requires coordinated control over participants, actions, interactions, scenes, and culture-specific constraints. We propose CARE, an evidence-grounded visual checklist framework for controllable cultural activity image generation. Given an activity prompt, CARE builds source-traceable cultural evidence, converts it into an optimized prompt and fine-grained checklist, verifies generated images with concrete VLM-based visual checks, and uses failed checks for targeted prompt repair. We introduce CARE-1360, a dataset of 1,360 cultural activity prompts across eight countries, and evaluate generated images with a unified human protocol. Experiments show that CARE consistently improves over direct generation and retrieval-based prompt refinement baselines across cultural and visual quality dimensions. Results with both ZImage and Stable Diffusion XL suggest that evidence-grounded visual checklists provide an interpretable control mechanism that transfers across the tested generation backends."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="deng-etal-2026-beyond-static">
<titleInfo>
<title>Beyond Static Symbols: Evidence-Grounded Visual Checklists for Cultural Activity Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hongcan</namePart>
<namePart type="family">Deng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bo</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yating</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rong</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhen</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xi</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rui</namePart>
<namePart type="family">Dong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Turghun</namePart>
<namePart type="family">Osman</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 2026 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</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">979-8-89176-459-0</identifier>
</relatedItem>
<abstract>Text-to-image models can render recognizable cultural symbols, but cultural activity generation requires coordinated control over participants, actions, interactions, scenes, and culture-specific constraints. We propose CARE, an evidence-grounded visual checklist framework for controllable cultural activity image generation. Given an activity prompt, CARE builds source-traceable cultural evidence, converts it into an optimized prompt and fine-grained checklist, verifies generated images with concrete VLM-based visual checks, and uses failed checks for targeted prompt repair. We introduce CARE-1360, a dataset of 1,360 cultural activity prompts across eight countries, and evaluate generated images with a unified human protocol. Experiments show that CARE consistently improves over direct generation and retrieval-based prompt refinement baselines across cultural and visual quality dimensions. Results with both ZImage and Stable Diffusion XL suggest that evidence-grounded visual checklists provide an interpretable control mechanism that transfers across the tested generation backends.</abstract>
<identifier type="citekey">deng-etal-2026-beyond-static</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.663/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>15267</start>
<end>15294</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Beyond Static Symbols: Evidence-Grounded Visual Checklists for Cultural Activity Generation
%A Deng, Hongcan
%A Ma, Bo
%A Yang, Yating
%A Ma, Rong
%A Wang, Zhen
%A Zhou, Xi
%A Dong, Rui
%A Osman, Turghun
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F deng-etal-2026-beyond-static
%X Text-to-image models can render recognizable cultural symbols, but cultural activity generation requires coordinated control over participants, actions, interactions, scenes, and culture-specific constraints. We propose CARE, an evidence-grounded visual checklist framework for controllable cultural activity image generation. Given an activity prompt, CARE builds source-traceable cultural evidence, converts it into an optimized prompt and fine-grained checklist, verifies generated images with concrete VLM-based visual checks, and uses failed checks for targeted prompt repair. We introduce CARE-1360, a dataset of 1,360 cultural activity prompts across eight countries, and evaluate generated images with a unified human protocol. Experiments show that CARE consistently improves over direct generation and retrieval-based prompt refinement baselines across cultural and visual quality dimensions. Results with both ZImage and Stable Diffusion XL suggest that evidence-grounded visual checklists provide an interpretable control mechanism that transfers across the tested generation backends.
%U https://aclanthology.org/2026.emnlp-main.663/
%P 15267-15294
Markdown (Informal)
[Beyond Static Symbols: Evidence-Grounded Visual Checklists for Cultural Activity Generation](https://aclanthology.org/2026.emnlp-main.663/) (Deng et al., EMNLP 2026)
ACL
- Hongcan Deng, Bo Ma, Yating Yang, Rong Ma, Zhen Wang, Xi Zhou, Rui Dong, and Turghun Osman. 2026. Beyond Static Symbols: Evidence-Grounded Visual Checklists for Cultural Activity Generation. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 15267–15294, Budapest, Hungary. Association for Computational Linguistics.