aiqbench analysis
This arXiv paper uses an art-and-critique project to probe gender bias in text-to-image generation. It pairs prompts for male and female construction workers and reports that outputs stress aesthetics and agility for women but authority and professionalism for men. The work is more qualitative and interpretive than a benchmark, so its value lies in the framing and the examples rather than in measured rates of bias. Readers building or evaluating generative image systems should treat its findings as illustrative evidence that prompt-level stereotyping persists, not as a quantified audit.
She Works, He Works: A Curious Exploration of Gender Bias in AI-Generated Imagery
arXiv:2407.18524v2 Announce Type: replace-cross Abstract: She Works, He Works is an interdisciplinary project that combines feminist visual theory, AI critique, and artistic practice to examine gender representation in AI-generated imagery. By juxtaposing text-to-image outputs of male and female construction workers, it reveals how societal biases manifest in generative AI systems. The study employs critically crafted prompts that blend traditionally gendered traits with unconventional contexts, exposing disparities in representation-emphasizing aesthetics and agility for women versus authority and professionalism for men. Grounded in Griselda Pollock's feminist insights on visual culture, the project positions AI as both a technological and cultural actor, capable of perpetuating stereotypes and enabling critique. As both a study and an artwork, the project underscores the transformative potential of AI to reimagine gender norms and inspire equitable narratives. It highlights the ethical implications of AI in creative industries, calling for transparent practices, diverse datasets, and reflexive engagement with AI's cultural impact. Through its integration of critical analysis and artistic exploration, She Works, He Works contributes to broader discussions on inclusive AI development and the role of art in fostering societal change. This dual approach showcases the power of AI as a medium for critique and a tool for envisioning more just and inclusive futures.
Abstract:She Works, He Works is an interdisciplinary project that combines feminist visual theory, AI critique, and artistic practice to examine gender representation in AI-generated imagery. By juxtaposing text-to-image outputs of male and female construction workers, it reveals how societal biases manifest in generative AI systems. The study employs critically crafted prompts that blend traditionally gendered traits with unconventional contexts, exposing disparities in representation-emphasizing aesthetics and agility for women versus authority and professionalism for men. Grounded in Griselda Pollock's feminist insights on visual culture, the project positions AI as both a technological and cultural actor, capable of perpetuating stereotypes and enabling critique. As both a study and an artwork, the project underscores the transformative potential of AI to reimagine gender norms and inspire equitable narratives. It highlights the ethical implications of AI in creative industries, calling for transparent practices, diverse datasets, and reflexive engagement with AI's cultural impact. Through its integration of critical analysis and artistic exploration, She Works, He Works contributes to broader discussions on inclusive AI development and the role of art in fostering societal change. This dual approach showcases the power of AI as a medium for critique and a tool for envisioning more just and inclusive futures.
9 pages, 8 figures. Published in the Proceedings of the 30th International Symposium on Electronic Art (ISEA 2025), Seoul, 2025. v2: substantially revised version as published at ISEA 2025 (v1 title: 'She Works, He Works: A Curious Exploration of Gender Bias in AI-Generated Imagery')
Computers and Society (cs.CY); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV)
I.2.0; J.5; K.4.2
arXiv:2407.18524 [cs.CY]
(or arXiv:2407.18524v2 [cs.CY] for this version)
Full text under the publisher's open licence · 268 words