mlsanityData to 7 Oct 2026

How well can Text-to-Image Generative Models understand Ethical Natural Language Interventions?

arXiv 2210.15230 ↗First posted 27 Oct 2022cs.CL cs.AI cs.LGcited by 92

Not on the map. Why?

Cited by 22 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Text-to-image generative models have achieved unprecedented success in generating high-quality images based on natural language descriptions. However, it is shown that these models tend to favor specific social groups when prompted with neutral text descriptions (e.g., 'a photo of a lawyer'). Following Zhao et al. (2021), we study the effect on the diversity of the generated images when adding ethical intervention that supports equitable judgment (e.g., 'if all individuals can be a lawyer irrespective of their gender') in the input prompts. To this end, we introduce an Ethical NaTural Language Interventions in Text-to-Image GENeration (ENTIGEN) benchmark dataset to evaluate the change in image generations conditional on ethical interventions across three social axes -- gender, skin color, and culture. Through ENTIGEN framework, we find that the generations from minDALL.E, DALL.E-mini and Stable Diffusion cover diverse social groups while preserving the image quality. Preliminary studies indicate that a large change in the model predictions is triggered by certain phrases such as 'irrespective of gender' in the context of gender bias in the ethical interventions. We release code and annotated data at https://github.com/Hritikbansal/entigen_emnlp.

Key facts. Cited by 92 papers in the map (data through 7 Oct 2026). Builds on 16 of its 25 references that are in the map. First posted on arXiv 27 Oct 2022.

Builds on

16 of 25 references.

References · 16

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  3. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
  4. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
  5. 2021Zero-Shot Text-to-Image Generationcited by 4,276
  6. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Modelscited by 3,595
  7. 2021Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Conceptscited by 1,209
  8. 2019Universal Adversarial Triggers for Attacking and Analyzing NLPcited by 709
  9. 2021CogView: Mastering Text-to-Image Generation via Transformerscited by 691
  10. 2021Multimodal datasets: misogyny, pornography, and malignant stereotypescited by 326
  11. 2021Harms of Gender Exclusivity and Challenges in Non-Binary Representation in Language Technologiescited by 128
  12. 2020Towards Controllable Biases in Language Generationcited by 112
4 more
  1. 2021Broaden the Vision: Geo-Diverse Visual Commonsense Reasoningcited by 59
  2. 2021Ethical-Advice Taker: Do Language Models Understand Natural Language Interventions?cited by 46
  3. 2020Towards an Atlas of Cultural Commonsense for Machine Reasoningcited by 28
  4. 2022The AI Index 2022 Annual Reportcited by 18

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 21; 2024: 37; 2025: 20; 2026: 13.

92 papers.

Sort:

By area:

  1. 2023Text-to-image Diffusion Models in Generative AI: A Surveycited by 264
  2. 2022Easily Accessible Text-to-Image Generation Amplifies Demographic Stereotypes at Large Scalecited by 262
  3. 2024VideoPhy: Evaluating Physical Commonsense for Video Generationcited by 215
  4. 2023Fair Diffusion: Instructing Text-to-Image Generation Models on Fairnesscited by 149
  5. 2023Leaving Reality to Imagination: Robust Classification via Generated Datasetscited by 91
  6. 2023Finetuning Text-to-Image Diffusion Models for Fairnesscited by 90
  7. 2023The Bias Amplification Paradox in Text-to-Image Generationcited by 69
  8. 2024Survey of Bias In Text-to-Image Generation: Definition, Evaluation, and Mitigationcited by 66
  9. 2023ITI-GEN: Inclusive Text-to-Image Generationcited by 64
  10. 2023AI's Regimes of Representation: A Community-centered Study of Text-to-Image Models in South Asiacited by 54
  11. 2023Inspecting the Geographical Representativeness of Images from Text-to-Image Modelscited by 44
  12. 2023If at First You Don't Succeed, Try, Try Again: Faithful Diffusion-based Text-to-Image Generation by Selectioncited by 40
38 more
  1. 2023T2IAT: Measuring Valence and Stereotypical Biases in Text-to-Image Generationcited by 39
  2. 2024FairRAG: Fair Human Generation via Fair Retrieval Augmentationcited by 34
  3. 2023Fair Text-to-Image Diffusion via Fair Mappingcited by 31
  4. 2024Uncovering Bias in Large Vision-Language Models at Scale with Counterfactualscited by 27
  5. 2023Stereotypes and Smut: The (Mis)representation of Non-cisgender Identities by Text-to-Image Modelscited by 26
  6. 2023A Friendly Face: Do Text-to-Image Systems Rely on Stereotypes when the Input is Under-Specified?cited by 25
  7. 2024TALC: Time-Aligned Captions for Multi-Scene Text-to-Video Generationcited by 25
  8. 2023Gender Biases in Automatic Evaluation Metrics for Image Captioningcited by 24
  9. 2024Improving Geo-diversity of Generated Images with Contextualized Vendi Score Guidancecited by 24
  10. 2023Auditing Gender Presentation Differences in Text-to-Image Modelscited by 22
  11. 2024Rethinking Training for De-biasing Text-to-Image Generation: Unlocking the Potential of Stable Diffusioncited by 22
  12. 2024Image Generation Diversity Issues and How to Tame Themcited by 22
  13. 2024FAIntbench: A Holistic and Precise Benchmark for Bias Evaluation in Text-to-Image Modelscited by 21
  14. 2023Mitigating stereotypical biases in text to image generative systemscited by 19
  15. 2024SANER: Annotation-free Societal Attribute Neutralizer for Debiasing CLIPcited by 19
  16. 2025Localized Cultural Knowledge is Conserved and Controllable in Large Language Modelscited by 19
  17. 2024BIGbench: A Unified Benchmark for Evaluating Multi-dimensional Social Biases in Text-to-Image Modelscited by 17
  18. 2024Towards Geographic Inclusion in the Evaluation of Text-to-Image Modelscited by 16
  19. 2024Multilingual Text-to-Image Generation Magnifies Gender Stereotypes and Prompt Engineering May Not Help Youcited by 15
  20. 2024Harm Amplification in Text-to-Image Modelscited by 14
  21. 2024BiasDora: Exploring Hidden Biased Associations in Vision-Language Modelscited by 12
  22. 2024Fairness and Bias Mitigation in Computer Vision: A Surveycited by 12
  23. 2025A Large Scale Analysis of Gender Biases in Text-to-Image Generative Modelscited by 12
  24. 2023DIG In: Evaluating Disparities in Image Generations with Indicators for Geographic Diversitycited by 9
  25. 2024Analyzing Quality, Bias, and Performance in Text-to-Image Generative Modelscited by 9
  26. 2023Vision + Language Applications: A Surveycited by 8
  27. 2023Diverse Diffusion: Enhancing Image Diversity in Text-to-Image Generationcited by 8
  28. 2025OASIS Uncovers: High-Quality T2I Models, Same Old Stereotypescited by 8
  29. 2024No Longer Trending on Artstation: Prompt Analysis of Generative AI Artcited by 7
  30. 2024Resampled Datasets Are Not Enough: Mitigating Societal Bias Beyond Single Attributescited by 7
  31. 2024FairQueue: Rethinking Prompt Learning for Fair Text-to-Image Generationcited by 7
  32. 2025Culture-TRIP: Culturally-Aware Text-to-Image Generation with Iterative Prompt Refinementcited by 7
  33. 2025FairGen: Controlling Sensitive Attributes for Fair Generations in Diffusion Models via Adaptive Latent Guidancecited by 7
  34. 2024The Male CEO and the Female Assistant: Evaluation and Mitigation of Gender Biases in Text-To-Image Generation of Dual Subjectscited by 6
  35. 2024The Factuality Tax of Diversity-Intervened Text-to-Image Generation: Benchmark and Fact-Augmented Interventioncited by 6
  36. 2024VersusDebias: Universal Zero-Shot Debiasing for Text-to-Image Models via SLM-Based Prompt Engineering and Generative Adversarycited by 6
  37. 2024Trustworthy Text-to-Image Diffusion Models: A Timely and Focused Surveycited by 6
  38. 2024Continuous Concepts Removal in Text-to-image Diffusion Modelscited by 6

50 most cited of 92 All 92 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025SafeGen: Embedding Ethical Safeguards in Text-to-Image Generation
  2. 2026BAFIS: Dataset + Framework to assess occupational Bias and Human Preference in modern Text-to-image Models
  3. 2024Can Prompt Modifiers Control Bias? A Comparative Analysis of Text-to-Image Generative Models
  4. 2026Newer Is Not Fairer: Gender Stereotyping in Text-to-Image AI Across Model Generations
  5. 2025Hidden Bias in the Machine: Stereotypes in Text-to-Image Models
  6. 2023Word-Level Explanations for Analyzing Bias in Text-to-Image Models
  7. 2022Ensuring Visual Commonsense Morality for Text-to-Image Generation
  8. 2023Exploring Social Bias in Downstream Applications of Text-to-Image Foundation Models