BAFIS supplies a new dataset and human-feedback framework demonstrating systematic gender and ethnicity biases in occupational image generation by five text-to-image models, with partial alignment between automated metrics and subjective ratings compared to German employment statistics.
Easily Ac- cessible Text-to-Image Generation Amplifies Demographic Stereotypes at Large Scale
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
Target-based prompting lets users define fairness distributions for skin tones in generative AI, shifting outputs closer to chosen targets across 36 tested prompts for occupations and contexts.
citing papers explorer
-
BAFIS: Dataset + Framework to assess occupational Bias and Human Preference in modern Text-to-image Models
BAFIS supplies a new dataset and human-feedback framework demonstrating systematic gender and ethnicity biases in occupational image generation by five text-to-image models, with partial alignment between automated metrics and subjective ratings compared to German employment statistics.
-
Who Defines Fairness? Target-Based Prompting for Demographic Representation in Generative Models
Target-based prompting lets users define fairness distributions for skin tones in generative AI, shifting outputs closer to chosen targets across 36 tested prompts for occupations and contexts.