BIGbench: A Unified Benchmark for Evaluating Multi-dimensional Social Biases in Text-to-Image Models
This work addresses the need for granular and automated bias assessment in text-to-image models, which is crucial for developers and researchers to mitigate social harms, though it is incremental as it builds on existing sociological classifications.
The authors tackled the problem of conflated social bias evaluations in text-to-image models by introducing BIGbench, a unified benchmark that classifies biases across four dimensions and uses automated multi-modal LLMs for evaluation, achieving high accuracy validated by human evaluators from diverse races.
Text-to-Image (T2I) generative models are becoming increasingly crucial due to their ability to generate high-quality images, but also raise concerns about social biases, particularly in human image generation. Sociological research has established systematic classifications of bias. Yet, existing studies on bias in T2I models largely conflate different types of bias, impeding methodological progress. In this paper, we introduce BIGbench, a unified benchmark for Biases of Image Generation, featuring a carefully designed dataset. Unlike existing benchmarks, BIGbench classifies and evaluates biases across four dimensions to enable a more granular evaluation and deeper analysis. Furthermore, BIGbench applies advanced multi-modal large language models to achieve fully automated and highly accurate evaluations. We apply BIGbench to evaluate eight representative T2I models and three debiasing methods. Our human evaluation results by trained evaluators from different races underscore BIGbench's effectiveness in aligning images and identifying various biases. Moreover, our study also reveals new research directions about biases with insightful analysis of our results. Our work is openly accessible at https://github.com/BIGbench2024/BIGbench2024/.