mlsanityData to 7 Oct 2026

BiasDora: Exploring Hidden Biased Associations in Vision-Language Models

arXiv 2407.02066 ↗First posted 2 Jul 2024cs.CLcited by 12

On the map: Multimodal LLMs / vision-language models → Social bias and fairness in VLMs

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.

Key facts. Cited by 12 papers in the map (data through 7 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.

Builds on

26 of 40 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024Uncovering Bias in Large Vision-Language Models at Scale with Counterfactuals30 May
  2. 2023VisoGender: A dataset for benchmarking gender bias in image-text pronoun resolution21 Jun

Other references · 24

  1. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  2. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  3. 2020StereoSet: Measuring stereotypical bias in pretrained language modelscited by 911
  4. 2016Semantics derived automatically from language corpora contain human-like biasescited by 894
  5. 2020CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Modelscited by 703
  6. 2019The Woman Worked as a Babysitter: On Biases in Language Generationcited by 540
  7. 2021BOLD: Dataset and Metrics for Measuring Biases in Open-Ended Language Generationcited by 410
  8. 2019On Measuring Social Biases in Sentence Encoderscited by 397
  9. 2019Mitigating Gender Bias in Natural Language Processing: Literature Reviewcited by 287
  10. 2019Measuring Bias in Contextualized Word Representationscited by 275
  11. 2022Easily Accessible Text-to-Image Generation Amplifies Demographic Stereotypes at Large Scalecited by 262
  12. 2022"I'm sorry to hear that": Finding New Biases in Language Models with a Holistic Descriptor Datasetcited by 160
12 more
  1. 2023Social Biases through the Text-to-Image Generation Lenscited by 126
  2. 2022How well can Text-to-Image Generative Models understand Ethical Natural Language Interventions?cited by 92
  3. 2024Investigating Bias in LLM-Based Bias Detection: Disparities between LLMs and Human Perceptioncited by 55
  4. 2023ROBBIE: Robust Bias Evaluation of Large Generative Language Modelscited by 53
  5. 2023Bias Against 93 Stigmatized Groups in Masked Language Models and Downstream Sentiment Classification Taskscited by 51
  6. 2023'Person' == Light-skinned, Western Man, and Sexualization of Women of Color: Stereotypes in Stable Diffusioncited by 33
  7. 2023Investigating Subtler Biases in LLMs: Ageism, Beauty, Institutional, and Nationality Bias in Generative Modelscited by 32
  8. 2023Social Bias Probing: Fairness Benchmarking for Language Modelscited by 29
  9. 2023A Friendly Face: Do Text-to-Image Systems Rely on Stereotypes when the Input is Under-Specified?cited by 25
  10. 2023Multimodal Composite Association Score: Measuring Gender Bias in Generative Multimodal Modelscited by 21
  11. 2023Multilingual large language models leak human stereotypes across language boundariescited by 12
  12. 2024Chain-of-Thought Prompting for Demographic Inference with Large Multimodal Modelscited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 3; 2025: 8; 2026: 1.

12 papers.

  1. 2025HumaniBench: A Human-Centric Framework for Large Multimodal Models Evaluationcited by 19
  2. 2025BBQ-V: Benchmarking Visual Stereotype Bias in Large Multimodal Modelscited by 10
  3. 2025MORALISE: A Structured Benchmark for Moral Alignment in Visual Language Modelscited by 10
  4. 2024Natural Language Inference Improves Compositionality in Vision-Language Modelscited by 8
  5. 2025Bias in Gender Bias Benchmarks: How Spurious Features Distort Evaluationcited by 5
  6. 2024Generated Bias: Auditing Internal Bias Dynamics of Text-To-Image Generative Modelscited by 3
  7. 2025DSO: Direct Steering Optimization for Bias Mitigationcited by 3
  8. 2025From Individuals to Interactions: Benchmarking Gender Bias in Multimodal Large Language Models from the Lens of Social Relationshipcited by 2
  9. 2025Data Matters Most: Auditing Social Bias in Contrastive Vision Language Modelscited by 1
  10. 2025Surgeons Are Indian Males and Speech Therapists Are White Females: Auditing Biases in Vision-Language Models for Healthcare Professionalscited by 1
  11. 2026CounterCount: A Diagnostic Framework for Counting Bias in Vision Language Modelscited by 1
  12. 2024Debias your Large Multi-Modal Model at Test-Time via Non-Contrastive Visual Attribute Steeringcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025VIGNETTE: Socially Grounded Bias Evaluation for Vision-Language Models
  2. 2025VisBias: Measuring Explicit and Implicit Social Biases in Vision Language Models
  3. 2024A Unified Framework and Dataset for Assessing Societal Bias in Vision-Language Models
  4. 2026Edu-MMBias: A Three-Tier Multimodal Benchmark for Auditing Social Bias in Vision-Language Models under Educational Contexts
  5. 2025Visual Cues of Gender and Race are Associated with Stereotyping in Vision-Language Models
  6. 2023Probing Intersectional Biases in Vision-Language Models with Counterfactual Examples
  7. 2024Identifying Implicit Social Biases in Vision-Language Models
  8. 2024Images Speak Louder than Words: Understanding and Mitigating Bias in Vision-Language Model from a Causal Mediation Perspective