# Counterfactually Measuring and Eliminating Social Bias in Vision-Language Pre-training Models

arXiv: https://arxiv.org/abs/2207.01056 · HTML: https://mlsanity.com/paper/2207.01056/

## Key facts

- Cited by 28 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 36 of its 45 references that are in the map.
- First posted on arXiv 3 Jul 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 36)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks](https://mlsanity.com/paper/1908.02265/) (2019)
- [Adversarial examples in the physical world](https://mlsanity.com/paper/1607.02533/) (2016)
- [Align before Fuse: Vision and Language Representation Learning with Momentum Distillation](https://mlsanity.com/paper/2107.07651/) (2021)
- [LXMERT: Learning Cross-Modality Encoder Representations from Transformers](https://mlsanity.com/paper/1908.07490/) (2019)
- [ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision](https://mlsanity.com/paper/2102.03334/) (2021)
- [Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks](https://mlsanity.com/paper/2004.06165/) (2020)
- [VL-BERT: Pre-training of Generic Visual-Linguistic Representations](https://mlsanity.com/paper/1908.08530/) (2019)
- [Semantics derived automatically from language corpora contain human-like biases](https://mlsanity.com/paper/1608.07187/) (2016)
- [Gender Bias in Coreference Resolution: Evaluation and Debiasing Methods](https://mlsanity.com/paper/1804.06876/) (2018)
- [A Corpus for Reasoning About Natural Language Grounded in Photographs](https://mlsanity.com/paper/1811.00491/) (2018)
- [Age Progression/Regression by Conditional Adversarial Autoencoder](https://mlsanity.com/paper/1702.08423/) (2017)
- [PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models](https://mlsanity.com/paper/2003.03808/) (2020)
- [Mitigating Gender Bias in Natural Language Processing: Literature Review](https://mlsanity.com/paper/1906.08976/) (2019)
- [Measuring Bias in Contextualized Word Representations](https://mlsanity.com/paper/1906.07337/) (2019)
- [Measuring and Reducing Gendered Correlations in Pre-trained Models](https://mlsanity.com/paper/2010.06032/) (2020)
- [Vision-Language Pre-Training with Triple Contrastive Learning](https://mlsanity.com/paper/2202.10401/) (2022)
- [Gender Bias in Contextualized Word Embeddings](https://mlsanity.com/paper/1904.03310/) (2019)
- [Fair Generative Modeling via Weak Supervision](https://mlsanity.com/paper/1910.12008/) (2019)
- [Bias Correction of Learned Generative Models using Likelihood-Free Importance Weighting](https://mlsanity.com/paper/1906.09531/) (2019)
- [Measuring Social Biases in Grounded Vision and Language Embeddings](https://mlsanity.com/paper/2002.08911/) (2020)
- [Worst of Both Worlds: Biases Compound in Pre-trained Vision-and-Language Models](https://mlsanity.com/paper/2104.08666/) (2021)
- [DeVLBert: Learning Deconfounded Visio-Linguistic Representations](https://mlsanity.com/paper/2008.06884/) (2020)

## Built on by (most cited first, 28 of 28)

- [Self-Introspective Decoding: Alleviating Hallucinations for Large Vision-Language Models](https://mlsanity.com/paper/2408.02032/) (2024)
- [CF-VLM:CounterFactual Vision-Language Fine-tuning](https://mlsanity.com/paper/2506.17267/) (2025)
- [Examining Gender and Racial Bias in Large Vision-Language Models Using a Novel Dataset of Parallel Images](https://mlsanity.com/paper/2402.05779/) (2024)
- [Fair Text-to-Image Diffusion via Fair Mapping](https://mlsanity.com/paper/2311.17695/) (2023)
- [GenderBias-VL: Benchmarking Gender Bias in Vision Language Models via Counterfactual Probing](https://mlsanity.com/paper/2407.00600/) (2024)
- [Survey of Social Bias in Vision-Language Models](https://mlsanity.com/paper/2309.14381/) (2023)
- [Gender Biases in Automatic Evaluation Metrics for Image Captioning](https://mlsanity.com/paper/2305.14711/) (2023)
- [Fairness and Bias in Multimodal AI: A Survey](https://mlsanity.com/paper/2406.19097/) (2024)
- [Model-Agnostic Gender Debiased Image Captioning](https://mlsanity.com/paper/2304.03693/) (2023)
- [New Job, New Gender? Measuring the Social Bias in Image Generation Models](https://mlsanity.com/paper/2401.00763/) (2024)
- [Revealing and Reducing Gender Biases in Vision and Language Assistants (VLAs)](https://mlsanity.com/paper/2410.19314/) (2024)
- [AI Sees Your Location, But With A Bias Toward The Wealthy World](https://mlsanity.com/paper/2502.11163/) (2025)
- [Images Speak Louder than Words: Understanding and Mitigating Bias in Vision-Language Model from a Causal Mediation Perspective](https://mlsanity.com/paper/2407.02814/) (2024)
- [FairDeDup: Detecting and Mitigating Vision-Language Fairness Disparities in Semantic Dataset Deduplication](https://mlsanity.com/paper/2404.16123/) (2024)
- [Adventures of Trustworthy Vision-Language Models: A Survey](https://mlsanity.com/paper/2312.04231/) (2023)
- [The Bias of Harmful Label Associations in Vision-Language Models](https://mlsanity.com/paper/2402.07329/) (2024)
- [Aligning Visual Contrastive learning models via Preference Optimization](https://mlsanity.com/paper/2411.08923/) (2024)
- [Self-Adaptive Cognitive Debiasing for Large Language Models in Decision-Making](https://mlsanity.com/paper/2504.04141/) (2025)
- [They're All Doctors: Synthesizing Diverse Counterfactuals to Mitigate Associative Bias](https://mlsanity.com/paper/2406.11331/) (2024)
- [Benign Shortcut for Debiasing: Fair Visual Recognition via Intervention with Shortcut Features](https://mlsanity.com/paper/2308.08482/) (2023)
- [Semantically Grounded QFormer for Efficient Vision Language Understanding](https://mlsanity.com/paper/2311.07449/) (2023)
- [GABInsight: Exploring Gender-Activity Binding Bias in Vision-Language Models](https://mlsanity.com/paper/2407.21001/) (2024)
- [TPC: Cross-Temporal Prediction Connection for Vision-Language Model Hallucination Reduction](https://mlsanity.com/paper/2503.04457/) (2025)
- [Measuring Social Bias in Vision-Language Models with Face-Only Counterfactuals from Real Photos](https://mlsanity.com/paper/2601.06931/) (2026)
- [DeepBias: Adaptive In-depth Probing of Social Biases in LVLMs](https://mlsanity.com/paper/2607.11228/) (2026)
- [Fair Visual Recognition via Intervention with Proxy Features](https://mlsanity.com/paper/2211.01253/) (2022)
- [Think Before You Act: A Two-Stage Framework for Mitigating Gender Bias Towards Vision-Language Tasks](https://mlsanity.com/paper/2405.16860/) (2024)
- [SDGBiasBench: Benchmarking and Mitigating Vision--Language Models' Biases in Sustainable Development Goals](https://mlsanity.com/paper/2605.21919/) (2026)

## Abstract (arXiv)

Vision-Language Pre-training (VLP) models have achieved state-of-the-art performance in numerous cross-modal tasks. Since they are optimized to capture the statistical properties of intra- and inter-modality, there remains risk to learn social biases presented in the data as well. In this work, we (1) introduce a counterfactual-based bias measurement CounterBias to quantify the social bias in VLP models by comparing the [MASK]ed prediction probabilities of factual and counterfactual samples; (2) construct a novel VL-Bias dataset including 24K image-text pairs for measuring gender bias in VLP models, from which we observed that significant gender bias is prevalent in VLP models; and (3) propose a VLP debiasing method FairVLP to minimize the difference in the [MASK]ed prediction probabilities between factual and counterfactual image-text pairs for VLP debiasing. Although CounterBias and FairVLP focus on social bias, they are generalizable to serve as tools and provide new insights to probe and regularize more knowledge in VLP models.