Lune

ACL Findings2023

T2IAT: Measuring Valence and Stereotypical Biases in Text-to-Image Generation

Jialu Wang, Xinyue Gabby Liu, Zonglin Di, Yang Liu, Xin Eric Wang

Abstract

Warning: This paper contains several contents that may be toxic, harmful, or offensive.

In the last few years, text-to-image generative models have gained remarkable success in generating images with unprecedented quality accompanied by a breakthrough of inference speed. Despite their rapid progress, human biases that manifest in the training examples, particularly with regard to common stereotypical biases, like gender and skin tone, still have been found in these generative models. In this work, we seek to measure more complex human biases exist in the task of text-to-image generations. Inspired by the well-known Implicit Association Test (IAT) from social psychology, we propose a novel Text-to-Image Association Test (T2IAT) framework that quantifies the implicit stereotypes between concepts and valence, and those in the images. We replicate the previously documented bias tests on generative models, including morally neutral tests on flowers and insects as well as demographic stereotypical tests on diverse social attributes. The results of these experiments demonstrate the presence of complex stereotypical behaviors in image generations.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

15 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • ViSAGe: A Global-Scale Analysis of Visual Stereotypes in Text-to-Image Generation cites High-Resolution Image Synthesis with Latent Diffusion Models
  • High-Resolution Image Synthesis with Latent Diffusion Models cites Denoising Diffusion Probabilistic Models
  • Finetuning Text-to-Image Diffusion Models for Fairness cites High-Resolution Image Synthesis with Latent Diffusion Models
  • Finetuning Text-to-Image Diffusion Models for Fairness cites Learning Transferable Visual Models From Natural Language Supervision
  • Finetuning Text-to-Image Diffusion Models for Fairness cites Denoising Diffusion Probabilistic Models
  • Finetuning Text-to-Image Diffusion Models for Fairness cites Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding
  • Learning Transferable Visual Models From Natural Language Supervision cites A Simple Framework for Contrastive Learning of Visual Representations
  • LightFair: Towards an Efficient Alternative for Fair T2I Diffusion via Debiasing Pre-trained Text Encoders cites High-Resolution Image Synthesis with Latent Diffusion Models
  • LightFair: Towards an Efficient Alternative for Fair T2I Diffusion via Debiasing Pre-trained Text Encoders cites Finetuning Text-to-Image Diffusion Models for Fairness
  • LightFair: Towards an Efficient Alternative for Fair T2I Diffusion via Debiasing Pre-trained Text Encoders cites Learning Transferable Visual Models From Natural Language Supervision
  • LightFair: Towards an Efficient Alternative for Fair T2I Diffusion via Debiasing Pre-trained Text Encoders cites Denoising Diffusion Probabilistic Models
  • New Job, New Gender? Measuring the Social Bias in Image Generation Models cites High-Resolution Image Synthesis with Latent Diffusion Models
  • New Job, New Gender? Measuring the Social Bias in Image Generation Models cites Learning Transferable Visual Models From Natural Language Supervision
  • Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding cites High-Resolution Image Synthesis with Latent Diffusion Models
  • Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding cites Learning Transferable Visual Models From Natural Language Supervision
  • Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding cites Denoising Diffusion Probabilistic Models
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers15

  1. Finetuning Text-to-Image Diffusion Models for FairnessXudong Shen, Chao Du, Tianyu Pang, Min Lin et al.ICLR 2024 · 97 citations
  2. Unmasking and Improving Data Credibility: A Study with Datasets for Training Harmless Language ModelsZhaowei Zhu, Jialu Wang, Hao Cheng, Yang LiuICLR 2024 · 30 citations
  3. New Job, New Gender? Measuring the Social Bias in Image Generation ModelsWenxuan Wang, Haonan Bai, Jen-tse Huang, Yuxuan Wan et al.ACM MM 2024 · 19 citations
  4. ViSAGe: A Global-Scale Analysis of Visual Stereotypes in Text-to-Image GenerationAkshita Jha, Vinodkumar Prabhakaran, Remi Denton, Sarah Laszlo et al.ACL 2024 · 18 citations
  5. LightFair: Towards an Efficient Alternative for Fair T2I Diffusion via Debiasing Pre-trained Text EncodersBoyu Han, Qianqian Xu, Shilong Bao, Zhiyong Yang et al.NeurIPS 2025 · 17 citations

Builds on18

  1. Learning Transferable Visual Models From Natural Language SupervisionAlec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh et al.ICML 2021 · 47,906 citations
  2. Denoising Diffusion Probabilistic ModelsJonathan Ho, Ajay Jain, Pieter AbbeelNeurIPS 2020 · 35,902 citations
  3. A Simple Framework for Contrastive Learning of Visual RepresentationsTing Chen, Simon Kornblith, Mohammad Norouzi, Geoffrey E. HintonICML 2020 · 24,064 citations
  4. High-Resolution Image Synthesis with Latent Diffusion ModelsRobin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser et al.CVPR 2022 · 13,123 citations
  5. Photorealistic Text-to-Image Diffusion Models with Deep Language UnderstandingChitwan Saharia, William Chan, Saurabh Saxena, Lala Li et al.NeurIPS 2022 · 8,965 citations

Related papers

  1. Association of Objects May Engender Stereotypes: Mitigating Association-Engendered Stereotypes in Text-to-Image GenerationJunlei Zhou, Jiashi Gao, Xiangyu Zhao, Xin Yao et al.NeurIPS 2024 · 5 citations
  2. Multi-Group Proportional Representations for Text-to-Image ModelsSangwon Jung, Alex Oesterling, Claudio Mayrink Verdun, Sajani Vithana et al.CVPR 2025
  3. OASIS Uncovers: High-Quality T2I Models, Same Old StereotypesSepehr Dehdashtian, Gautam Sreekumar, Vishnu BoddetiICLR 2025
  4. A Multi-dimensional study on Bias in Vision-Language modelsGabriele Ruggeri, Debora NozzaACL Findings 2023 · 7 citations
  5. ITI-Gen: Inclusive Text-to-Image GenerationCheng Zhang, Xuanbai Chen, Siqi Chai, Chen Henry Wu et al.ICCV 2023 · 89 citations
Dusk over the sea between two cliffs drawn in fine vertical lines