Seeing Symbols, Missing Cultures: Probing Vision-Language Models' Reasoning on Fire Imagery and Cultural Meaning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yu, Haorui, Zhao, Yang, Chu, Yijia, Yi, Qiufeng
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914254208106496
author Yu, Haorui
Zhao, Yang
Chu, Yijia
Yi, Qiufeng
author_facet Yu, Haorui
Zhao, Yang
Chu, Yijia
Yi, Qiufeng
contents Vision-Language Models (VLMs) often appear culturally competent but rely on superficial pattern matching rather than genuine cultural understanding. We introduce a diagnostic framework to probe VLM reasoning on fire-themed cultural imagery through both classification and explanation analysis. Testing multiple models on Western festivals, non-Western traditions, and emergency scenes reveals systematic biases: models correctly identify prominent Western festivals but struggle with underrepresented cultural events, frequently offering vague labels or dangerously misclassifying emergencies as celebrations. These failures expose the risks of symbolic shortcuts and highlight the need for cultural evaluation beyond accuracy metrics to ensure interpretable and fair multimodal systems.
format Preprint
id arxiv_https___arxiv_org_abs_2509_23311
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Seeing Symbols, Missing Cultures: Probing Vision-Language Models' Reasoning on Fire Imagery and Cultural Meaning
Yu, Haorui
Zhao, Yang
Chu, Yijia
Yi, Qiufeng
Computer Vision and Pattern Recognition
Artificial Intelligence
Computation and Language
Vision-Language Models (VLMs) often appear culturally competent but rely on superficial pattern matching rather than genuine cultural understanding. We introduce a diagnostic framework to probe VLM reasoning on fire-themed cultural imagery through both classification and explanation analysis. Testing multiple models on Western festivals, non-Western traditions, and emergency scenes reveals systematic biases: models correctly identify prominent Western festivals but struggle with underrepresented cultural events, frequently offering vague labels or dangerously misclassifying emergencies as celebrations. These failures expose the risks of symbolic shortcuts and highlight the need for cultural evaluation beyond accuracy metrics to ensure interpretable and fair multimodal systems.
title Seeing Symbols, Missing Cultures: Probing Vision-Language Models' Reasoning on Fire Imagery and Cultural Meaning
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2509.23311