@inproceedings{yu-etal-2025-seeing,
title = "Seeing Symbols, Missing Cultures: Probing Vision-Language Models' Reasoning on Fire Imagery and Cultural Meaning",
author = "Yu, Haorui and
Zhao, Yang and
Chu, Yijia and
Yi, Qiufeng",
editor = "Zhang, Chen and
Allaway, Emily and
Shen, Hua and
Miculicich, Lesly and
Li, Yinqiao and
M'hamdi, Meryem and
Limkonchotiwat, Peerat and
Bai, Richard He and
T.y.s.s., Santosh and
Han, Sophia Simeng and
Thapa, Surendrabikram and
Rim, Wiem Ben",
booktitle = "Proceedings of the 9th Widening NLP Workshop",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.winlp-main.1/",
doi = "10.18653/v1/2025.winlp-main.1",
pages = "1--8",
ISBN = "979-8-89176-351-7",
abstract = "Vision-Language Models (VLMs) often appearculturally competent but rely on superficial pat.tern matching rather than genuine cultural understanding. We introduce a diagnostic framework to probe VLM reasoning on fire-themedcultural imagery through both classification andexplanation analysis. Testing multiple modelson Western festivals, non-Western traditions.and emergency scenes reveals systematic biases: models correctly identify prominent Western festivals but struggle with underrepresentedcultural events, frequently offering vague labelsor dangerously misclassifying emergencies ascelebrations. These failures expose the risksof symbolic shortcuts and highlight the needfor cultural evaluation beyond accuracy metrics to ensure interpretable and fair multimodalsystems."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yu-etal-2025-seeing">
<titleInfo>
<title>Seeing Symbols, Missing Cultures: Probing Vision-Language Models’ Reasoning on Fire Imagery and Cultural Meaning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Haorui</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yijia</namePart>
<namePart type="family">Chu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qiufeng</namePart>
<namePart type="family">Yi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 9th Widening NLP Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chen</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emily</namePart>
<namePart type="family">Allaway</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hua</namePart>
<namePart type="family">Shen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lesly</namePart>
<namePart type="family">Miculicich</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yinqiao</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Meryem</namePart>
<namePart type="family">M’hamdi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peerat</namePart>
<namePart type="family">Limkonchotiwat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Richard</namePart>
<namePart type="given">He</namePart>
<namePart type="family">Bai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Santosh</namePart>
<namePart type="family">T.y.s.s.</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sophia</namePart>
<namePart type="given">Simeng</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Surendrabikram</namePart>
<namePart type="family">Thapa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wiem</namePart>
<namePart type="given">Ben</namePart>
<namePart type="family">Rim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-351-7</identifier>
</relatedItem>
<abstract>Vision-Language Models (VLMs) often appearculturally competent but rely on superficial pat.tern matching rather than genuine cultural understanding. We introduce a diagnostic framework to probe VLM reasoning on fire-themedcultural imagery through both classification andexplanation analysis. Testing multiple modelson Western festivals, non-Western traditions.and emergency scenes reveals systematic biases: models correctly identify prominent Western festivals but struggle with underrepresentedcultural events, frequently offering vague labelsor dangerously misclassifying emergencies ascelebrations. These failures expose the risksof symbolic shortcuts and highlight the needfor cultural evaluation beyond accuracy metrics to ensure interpretable and fair multimodalsystems.</abstract>
<identifier type="citekey">yu-etal-2025-seeing</identifier>
<identifier type="doi">10.18653/v1/2025.winlp-main.1</identifier>
<location>
<url>https://aclanthology.org/2025.winlp-main.1/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>1</start>
<end>8</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Seeing Symbols, Missing Cultures: Probing Vision-Language Models’ Reasoning on Fire Imagery and Cultural Meaning
%A Yu, Haorui
%A Zhao, Yang
%A Chu, Yijia
%A Yi, Qiufeng
%Y Zhang, Chen
%Y Allaway, Emily
%Y Shen, Hua
%Y Miculicich, Lesly
%Y Li, Yinqiao
%Y M’hamdi, Meryem
%Y Limkonchotiwat, Peerat
%Y Bai, Richard He
%Y T.y.s.s., Santosh
%Y Han, Sophia Simeng
%Y Thapa, Surendrabikram
%Y Rim, Wiem Ben
%S Proceedings of the 9th Widening NLP Workshop
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-351-7
%F yu-etal-2025-seeing
%X Vision-Language Models (VLMs) often appearculturally competent but rely on superficial pat.tern matching rather than genuine cultural understanding. We introduce a diagnostic framework to probe VLM reasoning on fire-themedcultural imagery through both classification andexplanation analysis. Testing multiple modelson Western festivals, non-Western traditions.and emergency scenes reveals systematic biases: models correctly identify prominent Western festivals but struggle with underrepresentedcultural events, frequently offering vague labelsor dangerously misclassifying emergencies ascelebrations. These failures expose the risksof symbolic shortcuts and highlight the needfor cultural evaluation beyond accuracy metrics to ensure interpretable and fair multimodalsystems.
%R 10.18653/v1/2025.winlp-main.1
%U https://aclanthology.org/2025.winlp-main.1/
%U https://doi.org/10.18653/v1/2025.winlp-main.1
%P 1-8
Markdown (Informal)
[Seeing Symbols, Missing Cultures: Probing Vision-Language Models’ Reasoning on Fire Imagery and Cultural Meaning](https://aclanthology.org/2025.winlp-main.1/) (Yu et al., WiNLP 2025)
ACL