Assessing Multilingual Fairness in Pre-trained Multimodal Representations

Recently pre-trained multimodal models, such as CLIP, have received a surge of attention for their exceptional capabilities towards connecting images and natural language. The textual representations in English can be desirably transferred to multilingualism and support promising downstream multimodal tasks for different languages. Nevertheless, previous fairness discourse in vision-and-language learning mainly focuses on monolingual representational biases, and rarely scrutinizes the principles of multilingual fairness in this multimodal setting, where one language is equated to a group of individuals and images provide the universal grounding for bridging different languages. In this paper, we provide a nuanced understanding of individual fairness and group fairness by viewing language as the recipient of fairness notions. We define new fairness notions within multilingual context and analytically articulate that, pre-trained vision-and-language representations are individually fair across languages but not guaranteed to group fairness. Furthermore, we conduct extensive experiments to explore the prevalent group disparity across languages and protected groups including race, gender and age.