Abstract
Abstract Text-to-image models, like Midjourney, DALL-E, and Stable Diffusion, have been shown to reinforce harmful biases, often perpetuating outdated and discriminatory stereotypes. In this study, we delve into a particular bias largely overlooked in generative image research: Brilliance Bias. By age 6, many children begin to internalize the damaging notion that intellectual brilliance is a male trait—a belief that persists into adulthood. Our findings demonstrate that popular image AI models possess this bias, further entrenching the misguided notion that exceptional intelligence is inherently male. This study calls for addressing brilliance bias in AI to ensure a more realistic representation of intellectual capabilities, helping shape a future where talent and brilliance are more broadly recognized.
Related Publications
Measures of Clustering Quality: A Working Set of Axioms for Clustering
Aiming towards the development of a general clustering theory, we discuss abstract axiomatization for clustering. In this respect, we follow up on the work of Kleinberg, ([1]) t...
Radiation Resistant Camera System for Monitoring Deuterium Plasma Discharges in the Large Helical Device
Radiation resistant camera system was constructed for monitoring deuterium plasma discharges in the Large Helical Device (LHD). This system has contributed to safe operation dur...
PROTEIN MEASUREMENT WITH THE FOLIN PHENOL REAGENT
Since 1922 when Wu proposed the use of the Folin phenol reagent for the measurement of proteins (l), a number of modified analytical procedures ut.ilizing this reagent have been...
Publication Info
- Year
- 2025
- Type
- article
- Citations
- 0
- Access
- Closed
External Links
Social Impact
Social media, news, blog, policy document mentions
Citation Metrics
Cite This
Identifiers
- DOI
- 10.1007/s00146-025-02752-6