Saved in:
Bibliographic Details
Main Authors: Kim, Jun Seong, Thu, Kyaw Ye, Ismayilzada, Javad, Park, Junyeong, Kim, Eunsu, Ahmad, Huzama, An, Na Min, Thorne, James, Oh, Alice
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2503.16826
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916658902204416
author Kim, Jun Seong
Thu, Kyaw Ye
Ismayilzada, Javad
Park, Junyeong
Kim, Eunsu
Ahmad, Huzama
An, Na Min
Thorne, James
Oh, Alice
author_facet Kim, Jun Seong
Thu, Kyaw Ye
Ismayilzada, Javad
Park, Junyeong
Kim, Eunsu
Ahmad, Huzama
An, Na Min
Thorne, James
Oh, Alice
contents In a highly globalized world, it is important for multi-modal large language models (MLLMs) to recognize and respond correctly to mixed-cultural inputs. For example, a model should correctly identify kimchi (Korean food) in an image both when an Asian woman is eating it, as well as an African man is eating it. However, current MLLMs show an over-reliance on the visual features of the person, leading to misclassification of the entities. To examine the robustness of MLLMs to different ethnicity, we introduce MixCuBe, a cross-cultural bias benchmark, and study elements from five countries and four ethnicities. Our findings reveal that MLLMs achieve both higher accuracy and lower sensitivity to such perturbation for high-resource cultures, but not for low-resource cultures. GPT-4o, the best-performing model overall, shows up to 58% difference in accuracy between the original and perturbed cultural settings in low-resource cultures. Our dataset is publicly available at: https://huggingface.co/datasets/kyawyethu/MixCuBe.
format Preprint
id arxiv_https___arxiv_org_abs_2503_16826
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle When Tom Eats Kimchi: Evaluating Cultural Bias of Multimodal Large Language Models in Cultural Mixture Contexts
Kim, Jun Seong
Thu, Kyaw Ye
Ismayilzada, Javad
Park, Junyeong
Kim, Eunsu
Ahmad, Huzama
An, Na Min
Thorne, James
Oh, Alice
Computation and Language
In a highly globalized world, it is important for multi-modal large language models (MLLMs) to recognize and respond correctly to mixed-cultural inputs. For example, a model should correctly identify kimchi (Korean food) in an image both when an Asian woman is eating it, as well as an African man is eating it. However, current MLLMs show an over-reliance on the visual features of the person, leading to misclassification of the entities. To examine the robustness of MLLMs to different ethnicity, we introduce MixCuBe, a cross-cultural bias benchmark, and study elements from five countries and four ethnicities. Our findings reveal that MLLMs achieve both higher accuracy and lower sensitivity to such perturbation for high-resource cultures, but not for low-resource cultures. GPT-4o, the best-performing model overall, shows up to 58% difference in accuracy between the original and perturbed cultural settings in low-resource cultures. Our dataset is publicly available at: https://huggingface.co/datasets/kyawyethu/MixCuBe.
title When Tom Eats Kimchi: Evaluating Cultural Bias of Multimodal Large Language Models in Cultural Mixture Contexts
topic Computation and Language
url https://arxiv.org/abs/2503.16826