LLM text-to-image models show demographic bias, new paper finds

A new research paper explores how Large Language Model (LLM)-based text conditioning in text-to-image (T2I) models can introduce demographic biases, even when demographic attributes are not specified in prompts. The study found that LLM-based systems exhibit stronger demographic skew compared to non-LLM baselines. Researchers identified system prompts as a key factor influencing these biases and proposed FairPro, a framework designed to generate fairness-aware instructions to mitigate disparities while preserving user intent. AI

IMPACT Highlights potential demographic biases in generative AI and offers a method to improve fairness in image generation.

RANK_REASON The cluster contains an academic paper detailing research findings on LLM-based text-to-image models and proposing a debiasing framework. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• FairPro
• Large Language Model
• NaHyeon Park
• text-to-image models

• paper
• safety

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →