mlsanityData to 7 Oct 2026

Uncovering Bias in Large Vision-Language Models at Scale with Counterfactuals

arXiv 2405.20152 ↗First posted 30 May 2024cs.CVcited by 27

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

Abstract (arXiv)

With the advent of Large Language Models (LLMs) possessing increasingly impressive capabilities, a number of Large Vision-Language Models (LVLMs) have been proposed to augment LLMs with visual inputs. Such models condition generated text on both an input image and a text prompt, enabling a variety of use cases such as visual question answering and multimodal chat. While prior studies have examined the social biases contained in text generated by LLMs, this topic has been relatively unexplored in LVLMs. Examining social biases in LVLMs is particularly challenging due to the confounding contributions of bias induced by information contained across the text and visual modalities. To address this challenging problem, we conduct a large-scale study of text generated by different LVLMs under counterfactual changes to input images, producing over 57 million responses from popular models. Our multi-dimensional bias evaluation framework reveals that social attributes such as perceived race, gender, and physical characteristics depicted in images can significantly influence the generation of toxic content, competency-associated words, harmful stereotypes, and numerical ratings of individuals.

Key facts. Cited by 27 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 29 of its 39 references that are in the map. First posted on arXiv 30 May 2024.

Builds on

29 of 39 references.

Closest ancestors · 5

Same direction, newest first

  1. 2024Examining Gender and Racial Bias in Large Vision-Language Models Using a Novel Dataset of Parallel Images8 Feb
  2. 2023SocialCounterfactuals: Probing and Mitigating Intersectional Social Biases in Vision-Language Models with Counterfactual Examples30 Nov
  3. 2023VisoGender: A dataset for benchmarking gender bias in image-text pronoun resolution21 Jun
  4. 2023DeAR: Debiasing Vision-Language Models with Additive Residuals18 Mar
  5. 2023MultiModal Bias: Introducing a Framework for Stereotypical Bias Assessment beyond Gender and Race in Vision Language Models16 Mar

Other references · 24

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2023GPT-4 Technical Reportcited by 18,132
  3. 2023Visual Instruction Tuningcited by 7,792
  4. 2023Improved Baselines with Visual Instruction Tuningcited by 4,362
  5. 2023InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuningcited by 2,855
  6. 2023G-Eval: NLG Evaluation using GPT-4 with Better Human Alignmentcited by 2,205
  7. 2020Language (Technology) is Power: A Critical Survey of "Bias" in NLPcited by 951
  8. 2020StereoSet: Measuring stereotypical bias in pretrained language modelscited by 911
  9. 2020CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Modelscited by 703
  10. 2018Gender Bias in Coreference Resolution: Evaluation and Debiasing Methodscited by 657
  11. 2018Gender Bias in Coreference Resolutioncited by 438
  12. 2023Is ChatGPT a Good NLG Evaluator? A Preliminary Studycited by 420
12 more
  1. 2022"I'm sorry to hear that": Finding New Biases in Language Models with a Holistic Descriptor Datasetcited by 160
  2. 2018Counterfactual Fairness in Text Classification through Robustnesscited by 150
  3. 2019Fairness-Aware Ranking in Search & Recommendation Systems with Application to LinkedIn Talent Searchcited by 137
  4. 2022How well can Text-to-Image Generative Models understand Ethical Natural Language Interventions?cited by 92
  5. 2019Toward Gender-Inclusive Coreference Resolutioncited by 84
  6. 2021Quantifying Social Biases in NLP: A Generalization and Empirical Comparison of Extrinsic Fairness Metricscited by 83
  7. 2021The Use and Misuse of Counterfactuals in Ethical Machine Learningcited by 52
  8. 2021Worst of Both Worlds: Biases Compound in Pre-trained Vision-and-Language Modelscited by 52
  9. 2023Bias Against 93 Stigmatized Groups in Masked Language Models and Downstream Sentiment Classification Taskscited by 51
  10. 2023On the Challenges of Using Black-Box APIs for Toxicity Evaluation in Researchcited by 44
  11. 2021Computer Vision and Conflicting Values: Describing People with Automated Alt Textcited by 14
  12. 2024LLaVA-Gemma: Accelerating Multimodal Foundation Models with a Compact Language Modelcited by 14

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 7; 2025: 8; 2026: 12.

27 papers.

Sort:

By area:

  1. 2025Thinking with Images for Multimodal Reasoning: Foundations, Methods, and Future Frontierscited by 193
  2. 2024GenderBias-VL: Benchmarking Gender Bias in Vision Language Models via Counterfactual Probingcited by 31
  3. 2024Revealing and Reducing Gender Biases in Vision and Language Assistants (VLAs)cited by 15
  4. 2024BiasDora: Exploring Hidden Biased Associations in Vision-Language Modelscited by 12
  5. 2024Fairness Definitions in Language Models Explainedcited by 10
  6. 2025FairI Tales: Evaluation of Fairness in Indian Contexts with a Focus on Bias and Stereotypescited by 9
  7. 2026Interpretable Debiasing of Vision-Language Models for Social Fairnesscited by 6
  8. 2024Debiasing Large Vision-Language Models by Ablating Protected Attribute Representationscited by 5
  9. 2024Lookism: The overlooked bias in computer visioncited by 4
  10. 2025LVLM-Compress-Bench: Benchmarking the Broader Impact of Large Vision-Language Model Compressioncited by 4
  11. 2025Person-Centric Annotations of LAION-400M: Auditing Bias and Its Transfer to Modelscited by 4
  12. 2025When Tom Eats Kimchi: Evaluating Cultural Bias of Multimodal Large Language Models in Cultural Mixture Contextscited by 3
15 more
  1. 2025When Algorithms Play Favorites: Lookism in the Generation and Perception of Facescited by 2
  2. 2026Measuring Social Bias in Vision-Language Models with Face-Only Counterfactuals from Real Photoscited by 2
  3. 2026Aesthetics as Structural Harm: Algorithmic Lookism Across Text-to-Image Generation and Classificationcited by 2
  4. 2026Cultural Counterfactuals: Evaluating Cultural Biases in Large Vision-Language Models with Counterfactual Examplescited by 2
  5. 2025A Stereotype Content Analysis on Color-related Social Bias in Large Vision Language Modelscited by 1
  6. 2025Interpreting Social Bias in LVLMs via Information Flow Analysis and Multi-Round Dialogue Evaluationcited by 1
  7. 2026Happy Young Women, Grumpy Old Men? Emotion-Driven Demographic Biases in Synthetic Face Generationcited by 1
  8. 2024Debias your Large Multi-Modal Model at Test-Time via Non-Contrastive Visual Attribute Steeringcited by 0
  9. 2026Prompts Without Evidence: How Neuroimaging Mentions Shift Clinical Vision-Language Model Predictionscited by 0
  10. 2026Cross-Cultural Value Attribution in Large Vision-Language Modelscited by 0
  11. 2026Symphony of Bias: Exploring Gender Associations with Musical Instruments in Multimodal LLMscited by 0
  12. 2026SportsGrounder: Proposal-Aided Interleaved Grounding for Dense Sports Video Reasoningcited by 0
  13. 2026ViD: Vision-Dominant Gender Bias Mitigation for Large Vision-Language Modelscited by 0
  14. 2026Visual Input and Its Framing Affect Attribute-based Descriptions Produced by Large Vision-Language Modelscited by 0
  15. 2026Same Chart, Different Story: Bias in Vision-Language Chart Interpretationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Uncovering Bias in Large Vision-Language Models with Counterfactuals
  2. 2024Identifying Implicit Social Biases in Vision-Language Models
  3. 2024A Unified Framework and Dataset for Assessing Societal Bias in Vision-Language Models
  4. 2025Bias in the Picture: Benchmarking VLMs with Social-Cue News Images and LLM-as-Judge Assessment
  5. 2025VIGNETTE: Socially Grounded Bias Evaluation for Vision-Language Models
  6. 2023Probing Intersectional Biases in Vision-Language Models with Counterfactual Examples
  7. 2025VisBias: Measuring Explicit and Implicit Social Biases in Vision Language Models
  8. 2024VLBiasBench: A Comprehensive Benchmark for Evaluating Bias in Large Vision-Language Model