mlsanityData to 14 Oct 2026

textttModSCAN: Measuring Stereotypical Bias in Large Vision-Language Models from Vision and Language Modalities

arXiv 2410.06967 ↗First posted 9 Oct 2024cs.CR cs.CYcited by 22

Not on the map. Why?

Abstract (arXiv)

Large vision-language models (LVLMs) have been rapidly developed and widely used in various fields, but the (potential) stereotypical bias in the model is largely unexplored. In this study, we present a pioneering measurement framework, textttModSCAN, to underlineSCAN the stereotypical bias within LVLMs from both vision and language underlineModalities. textttModSCAN examines stereotypical biases with respect to two typical stereotypical attributes (gender and race) across three kinds of scenarios: occupations, descriptors, and persona traits. Our findings suggest that 1) the currently popular LVLMs show significant stereotype biases, with CogVLM emerging as the most biased model; 2) these stereotypical biases may stem from the inherent biases in the training dataset and pre-trained models; 3) the utilization of specific prompt prefixes (from both vision and language modalities) performs well in reducing stereotypical biases. We believe our work can serve as the foundation for understanding and addressing stereotypical bias in LVLMs.

Key facts. Cited by 22 papers in the map (data through 14 Oct 2026). First posted on arXiv 9 Oct 2024.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 10; 2026: 12.

22 papers.

Sort:

By area:

  1. 2025Adjacent Words, Divergent Intents: Jailbreaking Large Language Models via Task Concurrencycited by 17
  2. 2025BBQ-V: Benchmarking Visual Stereotype Bias in Large Multimodal Modelscited by 11
  3. 2025AesBiasBench: Evaluating Bias and Alignment in Multimodal Language Models for Personalized Image Aesthetic Assessmentcited by 11
  4. 2026Sparse Models, Sparse Safety: Unsafe Routes in Mixture-of-Experts LLMscited by 9
  5. 2026Real Money, Fake Models: Deceptive Model Claims in Shadow APIscited by 8
  6. 2026Interpretable Debiasing of Vision-Language Models for Social Fairnesscited by 6
  7. 2025Bias in Gender Bias Benchmarks: How Spurious Features Distort Evaluationcited by 5
  8. 2025Characterizing Selective Refusal Bias in Large Language Modelscited by 4
  9. 2025VIGNETTE: Socially Grounded Bias Evaluation for Vision-Language Modelscited by 3
  10. 2026Moral Sycophancy in Vision Language Modelscited by 3
  11. 2026VIBE: Voice-Induced open-ended Bias Evaluation for Large Audio-Language Models via Real-World Speechcited by 3
  12. 2026Prototypicality Bias Reveals Blindspots in Multimodal Evaluation Metricscited by 2
10 more
  1. 2026When Understanding Becomes a Risk: Authenticity and Safety Risks in the Emerging Image Generation Paradigmcited by 2
  2. 2025Data Matters Most: Auditing Social Bias in Contrastive Vision Language Modelscited by 1
  3. 2025A Stereotype Content Analysis on Color-related Social Bias in Large Vision Language Modelscited by 1
  4. 2025Interpreting Social Bias in LVLMs via Information Flow Analysis and Multi-Round Dialogue Evaluationcited by 1
  5. 2026One-shot Optimized Steering Vector for Hallucination Mitigation for VLMscited by 1
  6. 2026StylisticBias: A Few Human Visual Cues Drive Most Social Biases in MLLMscited by 1
  7. 2025Is GPT-4o mini Blinded by its Own Safety Filters? Exposing the Multimodal-to-Unimodal Bottleneck in Hate Speech Detectioncited by 0
  8. 2026The Art of (Mis)alignment: How Fine-Tuning Methods Effectively Misalign and Realign LLMs in Post-Trainingcited by 0
  9. 2026Mitigating Bias in Large Vision-Language Models via Counterfactual Ensemble Decodingcited by 0
  10. 2026Guardrail-Agnostic Societal Bias Evaluation in Large Vision-Language Modelscited by 0