# Joint Vision-Language Social Bias Removal for CLIP

arXiv: https://arxiv.org/abs/2411.12785 · HTML: https://mlsanity.com/paper/2411.12785/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Builds on 54 of its 60 references that are in the map.
- First posted on arXiv 19 Nov 2024.

## Builds on (most cited first, 30 of 54)

- [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)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [Align before Fuse: Vision and Language Representation Learning with Momentum Distillation](https://mlsanity.com/paper/2107.07651/) (2021)
- [Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models](https://mlsanity.com/paper/1505.04870/) (2015)
- [Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings](https://mlsanity.com/paper/1607.06520/) (2016)
- [StereoSet: Measuring stereotypical bias in pretrained language models](https://mlsanity.com/paper/2004.09456/) (2020)
- [Semantics derived automatically from language corpora contain human-like biases](https://mlsanity.com/paper/1608.07187/) (2016)
- [Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference](https://mlsanity.com/paper/1902.01007/) (2019)
- [Robust fine-tuning of zero-shot models](https://mlsanity.com/paper/2109.01903/) (2021)
- [Certifying and removing disparate impact](https://mlsanity.com/paper/1412.3756/) (2014)
- [CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Models](https://mlsanity.com/paper/2010.00133/) (2020)
- [Long-tail learning via logit adjustment](https://mlsanity.com/paper/2007.07314/) (2020)
- [Just Train Twice: Improving Group Robustness without Training Group Information](https://mlsanity.com/paper/2107.09044/) (2021)
- [Null It Out: Guarding Protected Attributes by Iterative Nullspace Projection](https://mlsanity.com/paper/2004.07667/) (2020)
- [Age Progression/Regression by Conditional Adversarial Autoencoder](https://mlsanity.com/paper/1702.08423/) (2017)
- [On Measuring Social Biases in Sentence Encoders](https://mlsanity.com/paper/1903.10561/) (2019)
- [Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations](https://mlsanity.com/paper/2204.02937/) (2022)
- [Self-Diagnosis and Self-Debiasing: A Proposal for Reducing Corpus-Based Bias in NLP](https://mlsanity.com/paper/2103.00453/) (2021)
- [Multimodal datasets: misogyny, pornography, and malignant stereotypes](https://mlsanity.com/paper/2110.01963/) (2021)
- [Measuring and Reducing Gendered Correlations in Pre-trained Models](https://mlsanity.com/paper/2010.06032/) (2020)
- [Multiaccuracy: Black-Box Post-Processing for Fairness in Classification](https://mlsanity.com/paper/1805.12317/) (2018)
- [Probing Neural Network Comprehension of Natural Language Arguments](https://mlsanity.com/paper/1907.07355/) (2019)
- [Towards Debiasing Sentence Representations](https://mlsanity.com/paper/2007.08100/) (2020)
- [Debiasing Vision-Language Models via Biased Prompts](https://mlsanity.com/paper/2302.00070/) (2023)
- [Fairness-Aware Ranking in Search & Recommendation Systems with Application to LinkedIn Talent Search](https://mlsanity.com/paper/1905.01989/) (2019)
- [Evaluating CLIP: Towards Characterization of Broader Capabilities and Downstream Implications](https://mlsanity.com/paper/2108.02818/) (2021)
- [Turning a Blind Eye: Explicit Removal of Biases and Variation from Deep Neural Network Embeddings](https://mlsanity.com/paper/1809.02169/) (2018)

## Built on by (most cited first, 18 of 18)

- [Dimple: Discrete Diffusion Multimodal Large Language Model with Parallel Decoding](https://mlsanity.com/paper/2505.16990/) (2025)
- [Prompt-based Adaptation in Large-scale Vision Models: A Survey](https://mlsanity.com/paper/2510.13219/) (2025)
- [Bias Is a Subspace, Not a Coordinate: A Geometric Rethinking of Post-hoc Debiasing in Vision-Language Models](https://mlsanity.com/paper/2511.18123/) (2025)
- [Interpretable Debiasing of Vision-Language Models for Social Fairness](https://mlsanity.com/paper/2602.24014/) (2026)
- [Bias in Gender Bias Benchmarks: How Spurious Features Distort Evaluation](https://mlsanity.com/paper/2509.07596/) (2025)
- [Person-Centric Annotations of LAION-400M: Auditing Bias and Its Transfer to Models](https://mlsanity.com/paper/2510.03721/) (2025)
- [Backdoor-Powered Prompt Injection Attacks Nullify Defense Methods](https://mlsanity.com/paper/2510.03705/) (2025)
- [Bias Beyond Demographics: Probing Decision Boundaries in Black-Box LVLMs via Counterfactual VQA](https://mlsanity.com/paper/2508.03079/) (2025)
- [Measuring Social Bias in Vision-Language Models with Face-Only Counterfactuals from Real Photos](https://mlsanity.com/paper/2601.06931/) (2026)
- [FairSSL: Fair Multimodal Self-Supervised Learning](https://mlsanity.com/paper/2508.16748/) (2025)
- [Surgeons Are Indian Males and Speech Therapists Are White Females: Auditing Biases in Vision-Language Models for Healthcare Professionals](https://mlsanity.com/paper/2510.06280/) (2025)
- [SEM: Sparse Embedding Modulation for Post-Hoc Debiasing of Vision-Language Models](https://mlsanity.com/paper/2603.19028/) (2026)
- [Toward Robust Medical Fairness: Debiased Dual-Modal Alignment via Text-Guided Attribute-Disentangled Prompt Learning for Vision-Language Models](https://mlsanity.com/paper/2508.18886/) (2025)
- [Rank-Constrained Adaptation for Reliable Real-World Performance](https://mlsanity.com/paper/2602.06924/) (2026)
- [Intermediate Text Representation Guided Text-to-Image Generation for Enhancing One-and-Only Alignment](https://mlsanity.com/paper/2606.30262/) (2026)
- [Selective Test-Time Debiasing for CLIP via Reward Gating](https://mlsanity.com/paper/2607.00423/) (2026)
- [GGSS: Geodesic-Gated Spherical Steering for Inference-Time Debiasing of Generative Vision-Language Models](https://mlsanity.com/paper/2608.25375/) (2026)
- [Guardrail-Agnostic Societal Bias Evaluation in Large Vision-Language Models](https://mlsanity.com/paper/2608.29590/) (2026)

## Abstract (arXiv)

Vision-Language (V-L) pre-trained models such as CLIP show prominent capabilities in various downstream tasks. Despite this promise, V-L models are notoriously limited by their inherent social biases. A typical demonstration is that V-L models often produce biased predictions against specific groups of people, significantly undermining their real-world applicability. Existing approaches endeavor to mitigate the social bias problem in V-L models by removing biased attribute information from model embeddings. However, after our revisiting of these methods, we find that their bias removal is frequently accompanied by greatly compromised V-L alignment capabilities. We then reveal that this performance degradation stems from the unbalanced debiasing in image and text embeddings. To address this issue, we propose a novel V-L debiasing framework to align image and text biases followed by removing them from both modalities. By doing so, our method achieves multi-modal bias mitigation while maintaining the V-L alignment in the debiased embeddings. Additionally, we advocate a new evaluation protocol that can 1) holistically quantify the model debiasing and V-L alignment ability, and 2) evaluate the generalization of social bias removal models. We believe this work will offer new insights and guidance for future studies addressing the social bias problem in CLIP.