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

arXiv: https://arxiv.org/abs/2210.15230 · HTML: https://mlsanity.com/paper/2210.15230/

## Key facts

- Cited by 92 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 25 references that are in the map.
- First posted on arXiv 27 Oct 2022.

## Builds on (most cited first, 16 of 16)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models](https://mlsanity.com/paper/2112.10741/) (2021)
- [Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts](https://mlsanity.com/paper/2102.08981/) (2021)
- [Universal Adversarial Triggers for Attacking and Analyzing NLP](https://mlsanity.com/paper/1908.07125/) (2019)
- [CogView: Mastering Text-to-Image Generation via Transformers](https://mlsanity.com/paper/2105.13290/) (2021)
- [Multimodal datasets: misogyny, pornography, and malignant stereotypes](https://mlsanity.com/paper/2110.01963/) (2021)
- [Harms of Gender Exclusivity and Challenges in Non-Binary Representation in Language Technologies](https://mlsanity.com/paper/2108.12084/) (2021)
- [Towards Controllable Biases in Language Generation](https://mlsanity.com/paper/2005.00268/) (2020)
- [Broaden the Vision: Geo-Diverse Visual Commonsense Reasoning](https://mlsanity.com/paper/2109.06860/) (2021)
- [Ethical-Advice Taker: Do Language Models Understand Natural Language Interventions?](https://mlsanity.com/paper/2106.01465/) (2021)
- [Towards an Atlas of Cultural Commonsense for Machine Reasoning](https://mlsanity.com/paper/2009.05664/) (2020)
- [The AI Index 2022 Annual Report](https://mlsanity.com/paper/2205.03468/) (2022)

## Built on by (most cited first, 30 of 92)

- [Text-to-image Diffusion Models in Generative AI: A Survey](https://mlsanity.com/paper/2303.07909/) (2023)
- [Easily Accessible Text-to-Image Generation Amplifies Demographic Stereotypes at Large Scale](https://mlsanity.com/paper/2211.03759/) (2022)
- [VideoPhy: Evaluating Physical Commonsense for Video Generation](https://mlsanity.com/paper/2406.03520/) (2024)
- [Fair Diffusion: Instructing Text-to-Image Generation Models on Fairness](https://mlsanity.com/paper/2302.10893/) (2023)
- [Finetuning Text-to-Image Diffusion Models for Fairness](https://mlsanity.com/paper/2311.07604/) (2023)
- [Leaving Reality to Imagination: Robust Classification via Generated Datasets](https://mlsanity.com/paper/2302.02503/) (2023)
- [The Bias Amplification Paradox in Text-to-Image Generation](https://mlsanity.com/paper/2308.00755/) (2023)
- [Survey of Bias In Text-to-Image Generation: Definition, Evaluation, and Mitigation](https://mlsanity.com/paper/2404.01030/) (2024)
- [ITI-GEN: Inclusive Text-to-Image Generation](https://mlsanity.com/paper/2309.05569/) (2023)
- [AI's Regimes of Representation: A Community-centered Study of Text-to-Image Models in South Asia](https://mlsanity.com/paper/2305.11844/) (2023)
- [Inspecting the Geographical Representativeness of Images from Text-to-Image Models](https://mlsanity.com/paper/2305.11080/) (2023)
- [If at First You Don't Succeed, Try, Try Again: Faithful Diffusion-based Text-to-Image Generation by Selection](https://mlsanity.com/paper/2305.13308/) (2023)
- [T2IAT: Measuring Valence and Stereotypical Biases in Text-to-Image Generation](https://mlsanity.com/paper/2306.00905/) (2023)
- [FairRAG: Fair Human Generation via Fair Retrieval Augmentation](https://mlsanity.com/paper/2403.19964/) (2024)
- [Fair Text-to-Image Diffusion via Fair Mapping](https://mlsanity.com/paper/2311.17695/) (2023)
- [Uncovering Bias in Large Vision-Language Models at Scale with Counterfactuals](https://mlsanity.com/paper/2405.20152/) (2024)
- [Stereotypes and Smut: The (Mis)representation of Non-cisgender Identities by Text-to-Image Models](https://mlsanity.com/paper/2305.17072/) (2023)
- [A Friendly Face: Do Text-to-Image Systems Rely on Stereotypes when the Input is Under-Specified?](https://mlsanity.com/paper/2302.07159/) (2023)
- [TALC: Time-Aligned Captions for Multi-Scene Text-to-Video Generation](https://mlsanity.com/paper/2405.04682/) (2024)
- [Gender Biases in Automatic Evaluation Metrics for Image Captioning](https://mlsanity.com/paper/2305.14711/) (2023)
- [Improving Geo-diversity of Generated Images with Contextualized Vendi Score Guidance](https://mlsanity.com/paper/2406.04551/) (2024)
- [Auditing Gender Presentation Differences in Text-to-Image Models](https://mlsanity.com/paper/2302.03675/) (2023)
- [FAIntbench: A Holistic and Precise Benchmark for Bias Evaluation in Text-to-Image Models](https://mlsanity.com/paper/2405.17814/) (2024)
- [Rethinking Training for De-biasing Text-to-Image Generation: Unlocking the Potential of Stable Diffusion](https://mlsanity.com/paper/2408.12692/) (2024)
- [Image Generation Diversity Issues and How to Tame Them](https://mlsanity.com/paper/2411.16171/) (2024)
- [Localized Cultural Knowledge is Conserved and Controllable in Large Language Models](https://mlsanity.com/paper/2504.10191/) (2025)
- [Mitigating stereotypical biases in text to image generative systems](https://mlsanity.com/paper/2310.06904/) (2023)
- [SANER: Annotation-free Societal Attribute Neutralizer for Debiasing CLIP](https://mlsanity.com/paper/2408.10202/) (2024)
- [BIGbench: A Unified Benchmark for Evaluating Multi-dimensional Social Biases in Text-to-Image Models](https://mlsanity.com/paper/2407.15240/) (2024)
- [Towards Geographic Inclusion in the Evaluation of Text-to-Image Models](https://mlsanity.com/paper/2405.04457/) (2024)

## 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.