paper-with-me

홈 › Papers

Generated Bias: Auditing Internal Bias Dynamics of Text-To-Image Generative Models

2024-10-10 · Abhishek Mandal, Susan Leavy, Suzanne Little

Text-To-Image (TTI) Diffusion Models such as DALL-E and Stable Diffusion are capable of generating images from text prompts. However, they have been shown to perpetuate gender stereotypes. These models process data internally in multiple stages and employ several constituent models, often trained separately. In this paper, we propose two novel metrics to measure bias internally in these multistage multimodal models. Diffusion Bias was developed to detect and measures bias introduced by the diffusion stage of the models. Bias Amplification measures amplification of bias during the text-to-image conversion process. Our experiments reveal that TTI models amplify gender bias, the diffusion process itself contributes to bias and that Stable Diffusion v2 is more prone to gender bias than DALL-E 2.

📄 PDF Abstract BibTeX arXiv:2410.07884

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

White-Box Sensitivity Auditing with Steering Vectors

2026-01-23 · Hannah Cyberey, Yangfeng Ji, David Evans arxiv

Algorithmic audits are essential tools for examining systems for properties required by regulators or desired by operators. Current audits of large language models (LLMs) primarily rely on black-box evaluations that asse…

Interpretable Debiasing of Vision-Language Models for Social Fairness

2026-02-27 · Na Min An, Yoonna Jang, Yusuke Hirota, Ryo Hachiuma 외 arxiv

The rapid advancement of Vision-Language models (VLMs) has raised growing concerns that their black-box reasoning processes could lead to unintended forms of social bias. Current debiasing approaches focus on mitigating …

Smiling Women Pitching Down: Auditing Representational and Presentational Gender Biases in Image Generative AI

2023-05-17 · Luhang Sun, Mian Wei, Yibing Sun, Yoo Ji Suh 외

Generative AI models like DALL-E 2 can interpret textual prompts and generate high-quality images exhibiting human creativity. Though public enthusiasm is booming, systematic auditing of potential gender biases in AI-gen…

Benchmarking

Keeping Up with the Language Models: Systematic Benchmark Extension for Bias Auditing

2023-05-22 · Ioana Baldini, Chhavi Yadav, Manish Nagireddy, Payel Das 외

Bias auditing of language models (LMs) has received considerable attention as LMs are becoming widespread. As such, several benchmarks for bias auditing have been proposed. At the same time, the rapid evolution of LMs ca…

Reference-Based Bias Detection in LLMs via Relative Representations of Hidden States

2026-09-09 · Marek Jeliński, Jan Dubiński, Maciej Chrabaszcz, Sebastian Cygert arxiv

Existing bias auditing methods typically rely on model outputs, requiring costly benchmarks or judge models and potentially missing internal shifts that never appear in generated text. We propose a reference-based method…

Bias Detection