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

arXiv: https://arxiv.org/abs/2509.23311 · HTML: https://mlsanity.com/paper/2509.23311/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 5 of its 12 references that are in the map.
- First posted on arXiv 27 Sep 2025.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)
- Multimodal LLMs / vision-language models / [VLM benchmarks and visual reasoning](https://mlsanity.com/mllm/vlm-benchmarks-and-visual-reasoning/)

## Builds on (most cited first, 5 of 5)

- [Benchmarking Vision Language Models for Cultural Understanding](https://mlsanity.com/paper/2407.10920/) (2024)
- [CultureVLM: Characterizing and Improving Cultural Understanding of Vision-Language Models for over 100 Countries](https://mlsanity.com/paper/2501.01282/) (2025)
- [An Evaluation of Cultural Value Alignment in LLM](https://mlsanity.com/paper/2504.08863/) (2025)
- [See It from My Perspective: How Language Affects Cultural Bias in Image Understanding](https://mlsanity.com/paper/2406.11665/) (2024)
- [Multimodal Cultural Safety: Evaluation Framework and Alignment Strategies](https://mlsanity.com/paper/2505.14972/) (2025)

## Built on by (most cited first, 3 of 3)

- [VULCA-Bench: A Multicultural Vision-Language Benchmark for Evaluating Cultural Understanding](https://mlsanity.com/paper/2601.07986/) (2026)
- [Cross-Cultural Expert-Level Art Critique Evaluation with Vision-Language Models](https://mlsanity.com/paper/2601.07984/) (2026)
- [Computational Humor with Multimodal LLMs: Methods, Datasets, Evaluation, and Challenges](https://mlsanity.com/paper/2607.19011/) (2026)

## Abstract (arXiv)

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.