A Comparative Survey of Social Bias in Text and Image Generation: Gaps, Directions and Compliance with the EU AI Act

Abstract

Generative artificial intelligence models, including large language models and image generation models, are increasingly deployed in socially impactful domains. However, these models often exhibit social biases that can amplify stereotypes and produce harmful, discriminatory outputs. In this paper, we present a modality-comparative survey of social bias in text and image generation, structured around four components: benchmarks, bias identification, measurement, and mitigation. We systematically analyze methodological parallels and divergences across the two modalities, highlighting emerging research trends and identifying gaps. Finally, we map current image generation research efforts to the EU AI Act’s technical requirements, offering insights into how the community can advance towards more fair, safe, and trustworthy systems.

Ähnliche Arbeiten