# A Prompt Array Keeps the Bias Away: Debiasing Vision-Language Models with Adversarial Learning

arXiv: https://arxiv.org/abs/2203.11933 · HTML: https://mlsanity.com/paper/2203.11933/

## Key facts

- Cited by 104 papers in the map (data through 14 Oct 2026).
- Placed in Social bias and fairness in VLMs, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 62 of its 86 references that are in the map.
- First posted on arXiv 22 Mar 2022.

## Placed in

- Multimodal LLMs / vision-language models / [Social bias and fairness in VLMs](https://mlsanity.com/mllm/social-bias-and-fairness-in-vlms/)

## Builds on (most cited first, 30 of 62)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Learning to Prompt for Vision-Language Models](https://mlsanity.com/paper/2109.01134/) (2021)
- [Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing](https://mlsanity.com/paper/2107.13586/) (2021)
- [A Survey on Bias and Fairness in Machine Learning](https://mlsanity.com/paper/1908.09635/) (2019)
- [Align before Fuse: Vision and Language Representation Learning with Momentum Distillation](https://mlsanity.com/paper/2107.07651/) (2021)
- [Conditional Prompt Learning for Vision-Language Models](https://mlsanity.com/paper/2203.05557/) (2022)
- [Datasheets for Datasets](https://mlsanity.com/paper/1803.09010/) (2018)
- [Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings](https://mlsanity.com/paper/1607.06520/) (2016)
- [Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts](https://mlsanity.com/paper/2102.08981/) (2021)
- [Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval](https://mlsanity.com/paper/2104.00650/) (2021)
- [A Comprehensive Survey on Transfer Learning](https://mlsanity.com/paper/1911.02685/) (2019)
- [Ethical and social risks of harm from Language Models](https://mlsanity.com/paper/2112.04359/) (2021)
- [HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips](https://mlsanity.com/paper/1906.03327/) (2019)
- [Semantics derived automatically from language corpora contain human-like biases](https://mlsanity.com/paper/1608.07187/) (2016)
- [VGGSound: A Large-scale Audio-Visual Dataset](https://mlsanity.com/paper/2004.14368/) (2020)
- [LiT: Zero-Shot Transfer with Locked-image text Tuning](https://mlsanity.com/paper/2111.07991/) (2021)
- [SLIP: Self-supervision meets Language-Image Pre-training](https://mlsanity.com/paper/2112.12750/) (2021)
- [Age Progression/Regression by Conditional Adversarial Autoencoder](https://mlsanity.com/paper/1702.08423/) (2017)
- [Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraints](https://mlsanity.com/paper/1707.09457/) (2017)
- [Algorithmic decision making and the cost of fairness](https://mlsanity.com/paper/1701.08230/) (2017)
- [On Measuring Social Biases in Sentence Encoders](https://mlsanity.com/paper/1903.10561/) (2019)
- [Multimodal datasets: misogyny, pornography, and malignant stereotypes](https://mlsanity.com/paper/2110.01963/) (2021)
- [ActionCLIP: A New Paradigm for Video Action Recognition](https://mlsanity.com/paper/2109.08472/) (2021)
- [Prompting Visual-Language Models for Efficient Video Understanding](https://mlsanity.com/paper/2112.04478/) (2021)

## Built on by (most cited first, 30 of 104)

- [Forget-Me-Not: Learning to Forget in Text-to-Image Diffusion Models](https://mlsanity.com/paper/2303.17591/) (2023)
- [What does CLIP know about a red circle? Visual prompt engineering for VLMs](https://mlsanity.com/paper/2304.06712/) (2023)
- [Fair Diffusion: Instructing Text-to-Image Generation Models on Fairness](https://mlsanity.com/paper/2302.10893/) (2023)
- [Debiasing Vision-Language Models via Biased Prompts](https://mlsanity.com/paper/2302.00070/) (2023)
- [DeAR: Debiasing Vision-Language Models with Additive Residuals](https://mlsanity.com/paper/2303.10431/) (2023)
- [Contrastive Adapters for Foundation Model Group Robustness](https://mlsanity.com/paper/2207.07180/) (2022)
- [A CLIP-Hitchhiker's Guide to Long Video Retrieval](https://mlsanity.com/paper/2205.08508/) (2022)
- [Examining Gender and Racial Bias in Large Vision-Language Models Using a Novel Dataset of Parallel Images](https://mlsanity.com/paper/2402.05779/) (2024)
- [SocialCounterfactuals: Probing and Mitigating Intersectional Social Biases in Vision-Language Models with Counterfactual Examples](https://mlsanity.com/paper/2312.00825/) (2023)
- [Uncurated Image-Text Datasets: Shedding Light on Demographic Bias](https://mlsanity.com/paper/2304.02828/) (2023)
- [VisoGender: A dataset for benchmarking gender bias in image-text pronoun resolution](https://mlsanity.com/paper/2306.12424/) (2023)
- [Balancing Act: Distribution-Guided Debiasing in Diffusion Models](https://mlsanity.com/paper/2402.18206/) (2024)
- [Towards Safe Self-Distillation of Internet-Scale Text-to-Image Diffusion Models](https://mlsanity.com/paper/2307.05977/) (2023)
- [Exposing and Mitigating Spurious Correlations for Cross-Modal Retrieval](https://mlsanity.com/paper/2304.03391/) (2023)
- [CLIP the Bias: How Useful is Balancing Data in Multimodal Learning?](https://mlsanity.com/paper/2403.04547/) (2024)
- [Visual Tuning](https://mlsanity.com/paper/2305.06061/) (2023)
- [Fair Text-to-Image Diffusion via Fair Mapping](https://mlsanity.com/paper/2311.17695/) (2023)
- [Addressing Fairness Issues in Deep Learning-Based Medical Image Analysis: A Systematic Review](https://mlsanity.com/paper/2209.13177/) (2022)
- [Sociodemographic Bias in Language Models: A Survey and Forward Path](https://mlsanity.com/paper/2306.08158/) (2023)
- [Balancing the Picture: Debiasing Vision-Language Datasets with Synthetic Contrast Sets](https://mlsanity.com/paper/2305.15407/) (2023)
- [ToViLaG: Your Visual-Language Generative Model is Also An Evildoer](https://mlsanity.com/paper/2312.11523/) (2023)
- [Identifying Implicit Social Biases in Vision-Language Models](https://mlsanity.com/paper/2411.00997/) (2024)
- [Survey of Social Bias in Vision-Language Models](https://mlsanity.com/paper/2309.14381/) (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)
- [Stable Diffusion Exposed: Gender Bias from Prompt to Image](https://mlsanity.com/paper/2312.03027/) (2023)
- [FairerCLIP: Debiasing CLIP's Zero-Shot Predictions using Functions in RKHSs](https://mlsanity.com/paper/2403.15593/) (2024)
- [Zero-Shot Robustification of Zero-Shot Models](https://mlsanity.com/paper/2309.04344/) (2023)
- [Debiasing Methods for Fairer Neural Models in Vision and Language Research: A Survey](https://mlsanity.com/paper/2211.05617/) (2022)
- [Consensus and Subjectivity of Skin Tone Annotation for ML Fairness](https://mlsanity.com/paper/2305.09073/) (2023)
- [Looking for a Handsome Carpenter! Debiasing GPT-3 Job Advertisements](https://mlsanity.com/paper/2205.11374/) (2022)

## Abstract (arXiv)

Vision-language models can encode societal biases and stereotypes, but there are challenges to measuring and mitigating these multimodal harms due to lacking measurement robustness and feature degradation. To address these challenges, we investigate bias measures and apply ranking metrics for image-text representations. We then investigate debiasing methods and show that prepending learned embeddings to text queries that are jointly trained with adversarial debiasing and a contrastive loss reduces various bias measures with minimal degradation to the image-text representation.