Saved in:
Bibliographic Details
Main Authors: Kim, Eunsu, Park, Junyeong, An, Na Min, Kim, Junseong, Patel, Hitesh Laxmichand, Jin, Jiho, Kruk, Julia, Agarwal, Amit, Panda, Srikant, Ilasariya, Fenal Ashokbhai, Shim, Hyunjung, Oh, Alice
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.22787
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915664443211776
author Kim, Eunsu
Park, Junyeong
An, Na Min
Kim, Junseong
Patel, Hitesh Laxmichand
Jin, Jiho
Kruk, Julia
Agarwal, Amit
Panda, Srikant
Ilasariya, Fenal Ashokbhai
Shim, Hyunjung
Oh, Alice
author_facet Kim, Eunsu
Park, Junyeong
An, Na Min
Kim, Junseong
Patel, Hitesh Laxmichand
Jin, Jiho
Kruk, Julia
Agarwal, Amit
Panda, Srikant
Ilasariya, Fenal Ashokbhai
Shim, Hyunjung
Oh, Alice
contents In a globalized world, cultural elements from diverse origins frequently appear together within a single visual scene. We refer to these as culture mixing scenarios, yet how Large Vision-Language Models (LVLMs) perceive them remains underexplored. We investigate culture mixing as a critical challenge for LVLMs and examine how current models behave when cultural items from multiple regions appear together. To systematically analyze these behaviors, we construct CultureMix, a food Visual Question Answering (VQA) benchmark with 23k diffusion-generated, human-verified culture mixing images across four subtasks: (1) food-only, (2) food+food, (3) food+background, and (4) food+food+background. Evaluating 10 LVLMs, we find consistent failures to preserve individual cultural identities in mixed settings. Models show strong background reliance, with accuracy dropping 14% when cultural backgrounds are added to food-only baselines, and they produce inconsistent predictions for identical foods across different contexts. To address these limitations, we explore three robustness strategies. We find supervised fine-tuning using a diverse culture mixing dataset substantially improve model consistency and reduce background sensitivity. We call for increased attention to culture mixing scenarios as a critical step toward developing LVLMs capable of operating reliably in culturally diverse real-world environments.
format Preprint
id arxiv_https___arxiv_org_abs_2511_22787
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle World in a Frame: Understanding Culture Mixing as a New Challenge for Vision-Language Models
Kim, Eunsu
Park, Junyeong
An, Na Min
Kim, Junseong
Patel, Hitesh Laxmichand
Jin, Jiho
Kruk, Julia
Agarwal, Amit
Panda, Srikant
Ilasariya, Fenal Ashokbhai
Shim, Hyunjung
Oh, Alice
Computer Vision and Pattern Recognition
In a globalized world, cultural elements from diverse origins frequently appear together within a single visual scene. We refer to these as culture mixing scenarios, yet how Large Vision-Language Models (LVLMs) perceive them remains underexplored. We investigate culture mixing as a critical challenge for LVLMs and examine how current models behave when cultural items from multiple regions appear together. To systematically analyze these behaviors, we construct CultureMix, a food Visual Question Answering (VQA) benchmark with 23k diffusion-generated, human-verified culture mixing images across four subtasks: (1) food-only, (2) food+food, (3) food+background, and (4) food+food+background. Evaluating 10 LVLMs, we find consistent failures to preserve individual cultural identities in mixed settings. Models show strong background reliance, with accuracy dropping 14% when cultural backgrounds are added to food-only baselines, and they produce inconsistent predictions for identical foods across different contexts. To address these limitations, we explore three robustness strategies. We find supervised fine-tuning using a diverse culture mixing dataset substantially improve model consistency and reduce background sensitivity. We call for increased attention to culture mixing scenarios as a critical step toward developing LVLMs capable of operating reliably in culturally diverse real-world environments.
title World in a Frame: Understanding Culture Mixing as a New Challenge for Vision-Language Models
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2511.22787