# MultiModal Bias: Introducing a Framework for Stereotypical Bias Assessment beyond Gender and Race in Vision Language Models arXiv: https://arxiv.org/abs/2303.12734 ยท HTML: https://mlsanity.com/paper/2303.12734/ ## Key facts - Cited by 23 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 22 of its 41 references that are in the map. - First posted on arXiv 16 Mar 2023. ## 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, 22 of 22) - [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021) - [ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks](https://mlsanity.com/paper/1908.02265/) (2019) - [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) - [VisualBERT: A Simple and Performant Baseline for Vision and Language](https://mlsanity.com/paper/1908.03557/) (2019) - [ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision](https://mlsanity.com/paper/2102.03334/) (2021) - [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) - [Identifying and Reducing Gender Bias in Word-Level Language Models](https://mlsanity.com/paper/1904.03035/) (2019) - [Social Biases in NLP Models as Barriers for Persons with Disabilities](https://mlsanity.com/paper/2005.00813/) (2020) - [Detecting Emergent Intersectional Biases: Contextualized Word Embeddings Contain a Distribution of Human-like Biases](https://mlsanity.com/paper/2006.03955/) (2020) - [Black is to Criminal as Caucasian is to Police: Detecting and Removing Multiclass Bias in Word Embeddings](https://mlsanity.com/paper/1904.04047/) (2019) - [Evaluating CLIP: Towards Characterization of Broader Capabilities and Downstream Implications](https://mlsanity.com/paper/2108.02818/) (2021) - [Image Representations Learned With Unsupervised Pre-Training Contain Human-like Biases](https://mlsanity.com/paper/2010.15052/) (2020) - [Are Gender-Neutral Queries Really Gender-Neutral? Mitigating Gender Bias in Image Search](https://mlsanity.com/paper/2109.05433/) (2021) - [Does CLIP Benefit Visual Question Answering in the Medical Domain as Much as it Does in the General Domain?](https://mlsanity.com/paper/2112.13906/) (2021) - [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) - [Exposing and Correcting the Gender Bias in Image Captioning Datasets and Models](https://mlsanity.com/paper/1912.00578/) (2019) - [Assessing Multilingual Fairness in Pre-trained Multimodal Representations](https://mlsanity.com/paper/2106.06683/) (2021) - [Sentiment Analysis: Automatically Detecting Valence, Emotions, and Other Affectual States from Text](https://mlsanity.com/paper/2005.11882/) (2020) - [A study on the distribution of social biases in self-supervised learning visual models](https://mlsanity.com/paper/2203.01854/) (2022) ## Built on by (most cited first, 23 of 23) - [A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment](https://mlsanity.com/paper/2504.15585/) (2025) - [A Survey of State of the Art Large Vision Language Models: Alignment, Benchmark, Evaluations and Challenges](https://mlsanity.com/paper/2501.02189/) (2025) - [On the Challenges and Opportunities in Generative AI](https://mlsanity.com/paper/2403.00025/) (2024) - [GenderBias-VL: Benchmarking Gender Bias in Vision Language Models via Counterfactual Probing](https://mlsanity.com/paper/2407.00600/) (2024) - [Uncovering Bias in Large Vision-Language Models at Scale with Counterfactuals](https://mlsanity.com/paper/2405.20152/) (2024) - [MM-Soc: Benchmarking Multimodal Large Language Models in Social Media Platforms](https://mlsanity.com/paper/2402.14154/) (2024) - [VLBiasBench: A Comprehensive Benchmark for Evaluating Bias in Large Vision-Language Model](https://mlsanity.com/paper/2406.14194/) (2024) - [Revealing and Reducing Gender Biases in Vision and Language Assistants (VLAs)](https://mlsanity.com/paper/2410.19314/) (2024) - [Social Debiasing for Fair Multi-modal LLMs](https://mlsanity.com/paper/2408.06569/) (2024) - [Do VLMs Perceive or Recall? Probing Visual Perception vs. Memory with Classic Visual Illusions](https://mlsanity.com/paper/2601.22150/) (2026) - [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) - [FairPIVARA: Reducing and Assessing Biases in CLIP-Based Multimodal Models](https://mlsanity.com/paper/2409.19474/) (2024) - [Person-Centric Annotations of LAION-400M: Auditing Bias and Its Transfer to Models](https://mlsanity.com/paper/2510.03721/) (2025) - [DSO: Direct Steering Optimization for Bias Mitigation](https://mlsanity.com/paper/2512.15926/) (2025) - [Cultural Awareness in Vision-Language Models: A Cross-Country Exploration](https://mlsanity.com/paper/2505.20326/) (2025) - [Cultural Counterfactuals: Evaluating Cultural Biases in Large Vision-Language Models with Counterfactual Examples](https://mlsanity.com/paper/2603.02370/) (2026) - [Data Matters Most: Auditing Social Bias in Contrastive Vision Language Models](https://mlsanity.com/paper/2501.13223/) (2025) - [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) - [Think Before You Act: A Two-Stage Framework for Mitigating Gender Bias Towards Vision-Language Tasks](https://mlsanity.com/paper/2405.16860/) (2024) - [MoralCLIP: Contrastive Alignment of Vision-and-Language Representations with Moral Foundations Theory](https://mlsanity.com/paper/2506.05696/) (2025) - [IndicFairFace: Balanced Indian Face Dataset for Auditing and Mitigating Geographical Bias in Vision-Language Models](https://mlsanity.com/paper/2602.12659/) (2026) - [Addressing Overcommitment in the Reasoning of Gendered Economic Memes under Multimodal Ambiguity](https://mlsanity.com/paper/2610.11724/) (2026) ## Abstract (arXiv) Recent breakthroughs in self supervised training have led to a new class of pretrained vision language models. While there have been investigations of bias in multimodal models, they have mostly focused on gender and racial bias, giving much less attention to other relevant groups, such as minorities with regard to religion, nationality, sexual orientation, or disabilities. This is mainly due to lack of suitable benchmarks for such groups. We seek to address this gap by providing a visual and textual bias benchmark called MMBias, consisting of around 3,800 images and phrases covering 14 population subgroups. We utilize this dataset to assess bias in several prominent self supervised multimodal models, including CLIP, ALBEF, and ViLT. Our results show that these models demonstrate meaningful bias favoring certain groups. Finally, we introduce a debiasing method designed specifically for such large pre-trained models that can be applied as a post-processing step to mitigate bias, while preserving the remaining accuracy of the model.