Stereotypes and Smut: The (Mis)representation of Non-cisgender Identities by Text-to-Image Models
This work addresses the problem of harmful stereotypes and biases in AI-generated images for non-cisgender communities, highlighting a critical issue in AI fairness and representation.
The study investigated how text-to-image models represent non-cisgender identities, finding that these identities are consistently misrepresented as less human, more stereotyped, and more sexualized compared to cisgender ones. It also surveyed non-cisgender individuals, who expressed concerns about misrepresentation and harmful impacts, rejecting simple fixes in favor of community involvement and curated data.
Cutting-edge image generation has been praised for producing high-quality images, suggesting a ubiquitous future in a variety of applications. However, initial studies have pointed to the potential for harm due to predictive bias, reflecting and potentially reinforcing cultural stereotypes. In this work, we are the first to investigate how multimodal models handle diverse gender identities. Concretely, we conduct a thorough analysis in which we compare the output of three image generation models for prompts containing cisgender vs. non-cisgender identity terms. Our findings demonstrate that certain non-cisgender identities are consistently (mis)represented as less human, more stereotyped and more sexualised. We complement our experimental analysis with (a)~a survey among non-cisgender individuals and (b) a series of interviews, to establish which harms affected individuals anticipate, and how they would like to be represented. We find respondents are particularly concerned about misrepresentation, and the potential to drive harmful behaviours and beliefs. Simple heuristics to limit offensive content are widely rejected, and instead respondents call for community involvement, curated training data and the ability to customise. These improvements could pave the way for a future where change is led by the affected community, and technology is used to positively ``[portray] queerness in ways that we haven't even thought of'' rather than reproducing stale, offensive stereotypes.