# BiasDora: Exploring Hidden Biased Associations in Vision-Language Models

arXiv: https://arxiv.org/abs/2407.02066 · HTML: https://mlsanity.com/paper/2407.02066/

## Key facts

- Cited by 12 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 26 of its 40 references that are in the map.
- First posted on arXiv 2 Jul 2024.

## 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, 26 of 26)

- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [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)
- [CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Models](https://mlsanity.com/paper/2010.00133/) (2020)
- [The Woman Worked as a Babysitter: On Biases in Language Generation](https://mlsanity.com/paper/1909.01326/) (2019)
- [BOLD: Dataset and Metrics for Measuring Biases in Open-Ended Language Generation](https://mlsanity.com/paper/2101.11718/) (2021)
- [On Measuring Social Biases in Sentence Encoders](https://mlsanity.com/paper/1903.10561/) (2019)
- [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)
- [Easily Accessible Text-to-Image Generation Amplifies Demographic Stereotypes at Large Scale](https://mlsanity.com/paper/2211.03759/) (2022)
- ["I'm sorry to hear that": Finding New Biases in Language Models with a Holistic Descriptor Dataset](https://mlsanity.com/paper/2205.09209/) (2022)
- [Social Biases through the Text-to-Image Generation Lens](https://mlsanity.com/paper/2304.06034/) (2023)
- [How well can Text-to-Image Generative Models understand Ethical Natural Language Interventions?](https://mlsanity.com/paper/2210.15230/) (2022)
- [Investigating Bias in LLM-Based Bias Detection: Disparities between LLMs and Human Perception](https://mlsanity.com/paper/2403.14896/) (2024)
- [ROBBIE: Robust Bias Evaluation of Large Generative Language Models](https://mlsanity.com/paper/2311.18140/) (2023)
- [VisoGender: A dataset for benchmarking gender bias in image-text pronoun resolution](https://mlsanity.com/paper/2306.12424/) (2023)
- [Bias Against 93 Stigmatized Groups in Masked Language Models and Downstream Sentiment Classification Tasks](https://mlsanity.com/paper/2306.05550/) (2023)
- ['Person' == Light-skinned, Western Man, and Sexualization of Women of Color: Stereotypes in Stable Diffusion](https://mlsanity.com/paper/2310.19981/) (2023)
- [Investigating Subtler Biases in LLMs: Ageism, Beauty, Institutional, and Nationality Bias in Generative Models](https://mlsanity.com/paper/2309.08902/) (2023)
- [Social Bias Probing: Fairness Benchmarking for Language Models](https://mlsanity.com/paper/2311.09090/) (2023)
- [Uncovering Bias in Large Vision-Language Models at Scale with Counterfactuals](https://mlsanity.com/paper/2405.20152/) (2024)
- [A Friendly Face: Do Text-to-Image Systems Rely on Stereotypes when the Input is Under-Specified?](https://mlsanity.com/paper/2302.07159/) (2023)
- [Multimodal Composite Association Score: Measuring Gender Bias in Generative Multimodal Models](https://mlsanity.com/paper/2304.13855/) (2023)
- [Multilingual large language models leak human stereotypes across language boundaries](https://mlsanity.com/paper/2312.07141/) (2023)
- [Chain-of-Thought Prompting for Demographic Inference with Large Multimodal Models](https://mlsanity.com/paper/2405.15687/) (2024)

## Built on by (most cited first, 12 of 12)

- [HumaniBench: A Human-Centric Framework for Large Multimodal Models Evaluation](https://mlsanity.com/paper/2505.11454/) (2025)
- [BBQ-V: Benchmarking Visual Stereotype Bias in Large Multimodal Models](https://mlsanity.com/paper/2502.08779/) (2025)
- [MORALISE: A Structured Benchmark for Moral Alignment in Visual Language Models](https://mlsanity.com/paper/2505.14728/) (2025)
- [Natural Language Inference Improves Compositionality in Vision-Language Models](https://mlsanity.com/paper/2410.22315/) (2024)
- [Bias in Gender Bias Benchmarks: How Spurious Features Distort Evaluation](https://mlsanity.com/paper/2509.07596/) (2025)
- [Generated Bias: Auditing Internal Bias Dynamics of Text-To-Image Generative Models](https://mlsanity.com/paper/2410.07884/) (2024)
- [DSO: Direct Steering Optimization for Bias Mitigation](https://mlsanity.com/paper/2512.15926/) (2025)
- [From Individuals to Interactions: Benchmarking Gender Bias in Multimodal Large Language Models from the Lens of Social Relationship](https://mlsanity.com/paper/2506.23101/) (2025)
- [Data Matters Most: Auditing Social Bias in Contrastive Vision Language Models](https://mlsanity.com/paper/2501.13223/) (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)
- [CounterCount: A Diagnostic Framework for Counting Bias in Vision Language Models](https://mlsanity.com/paper/2605.17826/) (2026)
- [Debias your Large Multi-Modal Model at Test-Time via Non-Contrastive Visual Attribute Steering](https://mlsanity.com/paper/2411.12590/) (2024)

## Abstract (arXiv)

Existing works examining Vision-Language Models (VLMs) for social biases predominantly focus on a limited set of documented bias associations, such as gender:profession or race:crime. This narrow scope often overlooks a vast range of unexamined implicit associations, restricting the identification and, hence, mitigation of such biases. We address this gap by probing VLMs to (1) uncover hidden, implicit associations across 9 bias dimensions. We systematically explore diverse input and output modalities and (2) demonstrate how biased associations vary in their negativity, toxicity, and extremity. Our work (3) identifies subtle and extreme biases that are typically not recognized by existing methodologies. We make the Dataset of retrieved associations, (Dora), publicly available here https://github.com/chahatraj/BiasDora.