Understanding Social Bias in Multimodal Learning Systems: A Taxonomy and Framework

Abstract

The rapid adoption of multimodal learning systems across high-stakes applications has intensified concerns about fairness and social bias, yet existing research remains scattered across modalities, tasks, protected attributes, mitigation strategies, and evaluation methodologies. This survey provides an overview of fairness and social bias in multimodal artificial intelligence. By reviewing 44 papers and 16 datasets, we synthesize the current landscape of fairness research in multimodal systems and identify emerging challenges and research opportunities. Our primary contribution is twofold. First, we introduce a multi-dimensional taxonomy that organizes the literature across nine operational dimensions, providing a unified perspective on multimodal fairness research. Second, we propose an end-to-end operational lifecycle framework that illustrates how biases emerge within shared latent spaces and identifies targeted pre-processing, training-time, and post-training intervention strategies. Overall, this survey discusses key performance-fairness trade-offs and provides a structured roadmap for evaluating and mitigating bias, ultimately supporting the development of more equitable multimodal AI systems.