Exploring Visual Culture Awareness in GPT-4V: A Comprehensive Probing
Cao, Yong, Li, Wenyan, Li, Jiaang, Yuan, Yifei, Hershcovich, Daniel
–arXiv.org Artificial Intelligence
Pretrained large Vision-Language models have drawn considerable interest in recent years due to their remarkable performance. Despite considerable efforts to assess these models from diverse perspectives, the extent of visual cultural awareness in the state-of-the-art GPT-4V model remains unexplored. To tackle this gap, we extensively probed GPT-4V using the MaRVL benchmark dataset, aiming to investigate its capabilities and limitations in visual understanding with a focus on cultural aspects. Specifically, we introduced three visual related tasks, i.e. caption classification, pairwise captioning, and culture tag selection, to systematically delve into fine-grained visual cultural evaluation. Experimental results indicate that GPT-4V excels at identifying cultural concepts but still exhibits weaker performance in low-resource languages, such as Tamil and Swahili. Notably, through human evaluation, GPT-4V proves to be more culturally relevant in image captioning tasks than the original MaRVL human annotations, suggesting a promising solution for future visual cultural benchmark construction.
arXiv.org Artificial Intelligence
Feb-8-2024
- Country:
- Asia > Middle East (0.14)
- Europe > Croatia (0.14)
- North America
- Canada (0.14)
- United States (0.14)
- Genre:
- Research Report (0.84)
- Technology:
- Information Technology > Artificial Intelligence
- Machine Learning
- Neural Networks > Deep Learning (0.31)
- Performance Analysis > Accuracy (0.47)
- Natural Language > Large Language Model (1.00)
- Vision (1.00)
- Machine Learning
- Information Technology > Artificial Intelligence