Can we Debias Social Stereotypes in AI-Generated Images? Examining Text-to-Image Outputs and User Perceptions
Recent advances in generative AI have enabled visual content creation through text-to-image (T2I) generation. However, despite their creative potential, T2I models often replicate and amplify societal stereotypes -- particularly those related to gender, race, and culture -- raising important ethical concerns. This paper proposes a theory-driven bias detection rubric and a Social Stereotype Index (SSI) to systematically evaluate social biases in T2I outputs. We audited three major T2I model outputs -- DALL-E-3, Midjourney-6.1, and Stability AI Core -- using 100 queries across three categories -- geocultural, occupational, and adjectival. Our analysis reveals that initial outputs are prone to include stereotypical visual cues, including gendered professions, cultural markers, and western beauty norms. To address this, we adopted our rubric to conduct targeted prompt refinement using LLMs, which significantly reduced bias -- SSI dropped by 61% for geocultural, 69% for occupational, and 51% for adjectival queries. We complemented our quantitative analysis through a user study examining perceptions, awareness, and preferences around AI-generated biased imagery. Our findings reveal a key tension -- although prompt refinement can mitigate stereotypes, it can limit contextual alignment. Interestingly, users often perceived stereotypical images to be more aligned with their expectations. We discuss the need to balance ethical debiasing with contextual relevance and call for T2I systems that support global diversity and inclusivity while not compromising the reflection of real-world social complexity.
Code (0)
등록된 구현이 없습니다.
Tasks
Bias DetectionSimilar Papers 제목 키워드 기반
Social-Group-Agnostic Word Embedding Debiasing via the Stereotype Content Model
Existing word embedding debiasing methods require social-group-specific word pairs (e.g., "man"-"woman") for each social attribute (e.g., gender), which cannot be used to mitigate bias for other social groups, making the…
AttributeDebiasing Pretrained Text Encoders by Paying Attention to Paying Attention
Recent studies in fair Representation Learning have observed a strong inclination for natural language processing (NLP) models to exhibit discriminatory stereotypes across gender, religion, race and many such social cons…
FairnessRepresentation LearningSentenceWord EmbeddingsSelf-Debiasing Large Language Models: Zero-Shot Recognition and Reduction of Stereotypes
Large language models (LLMs) have shown remarkable advances in language generation and understanding but are also prone to exhibiting harmful social biases. While recognition of these behaviors has generated an abundance…
Text GenerationZero-Shot LearningQueer People are People First: Deconstructing Sexual Identity Stereotypes in Large Language Models
Large Language Models (LLMs) are trained primarily on minimally processed web text, which exhibits the same wide range of social biases held by the humans who created that content. Consequently, text generated by LLMs ca…
SentenceAnti-stereotypical Predictive Text Suggestions Do Not Reliably Yield Anti-stereotypical Writing
AI-based systems such as language models can replicate and amplify social biases reflected in their training data. Among other questionable behavior, this can lead to LM-generated text--and text suggestions--that contain…
Language ModelingLanguage Modelling