# More Distinctively Black and Feminine Faces Lead to Increased Stereotyping in Vision-Language Models

arXiv: https://arxiv.org/abs/2407.06194 · HTML: https://mlsanity.com/paper/2407.06194/

## Key facts

- No citing papers in the map yet (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 24 of its 57 references that are in the map.
- First posted on arXiv 22 May 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, 24 of 24)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [CoCa: Contrastive Captioners are Image-Text Foundation Models](https://mlsanity.com/paper/2205.01917/) (2022)
- [Language (Technology) is Power: A Critical Survey of "Bias" in NLP](https://mlsanity.com/paper/2005.14050/) (2020)
- [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)
- [Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2307.15217/) (2023)
- [A Survey on In-context Learning](https://mlsanity.com/paper/2301.00234/) (2022)
- [The Woman Worked as a Babysitter: On Biases in Language Generation](https://mlsanity.com/paper/1909.01326/) (2019)
- [Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Tasks](https://mlsanity.com/paper/2208.10442/) (2022)
- [On Measuring Social Biases in Sentence Encoders](https://mlsanity.com/paper/1903.10561/) (2019)
- [Easily Accessible Text-to-Image Generation Amplifies Demographic Stereotypes at Large Scale](https://mlsanity.com/paper/2211.03759/) (2022)
- [Word Embeddings Quantify 100 Years of Gender and Ethnic Stereotypes](https://mlsanity.com/paper/1711.08412/) (2017)
- [Marked Personas: Using Natural Language Prompts to Measure Stereotypes in Language Models](https://mlsanity.com/paper/2305.18189/) (2023)
- [Social Biases through the Text-to-Image Generation Lens](https://mlsanity.com/paper/2304.06034/) (2023)
- [Understanding and Evaluating Racial Biases in Image Captioning](https://mlsanity.com/paper/2106.08503/) (2021)
- [Large Language Models Portray Socially Subordinate Groups as More Homogeneous, Consistent with a Bias Observed in Humans](https://mlsanity.com/paper/2401.08495/) (2024)
- [Smiling Women Pitching Down: Auditing Representational and Presentational Gender Biases in Image Generative AI](https://mlsanity.com/paper/2305.10566/) (2023)
- [Quantitative Evaluation of Gender Bias in Astronomical Publications from Citation Counts](https://mlsanity.com/paper/1610.08984/) (2016)

## Abstract (arXiv)

Vision Language Models (VLMs), exemplified by GPT-4V, adeptly integrate text and vision modalities. This integration enhances Large Language Models' ability to mimic human perception, allowing them to process image inputs. Despite VLMs' advanced capabilities, however, there is a concern that VLMs inherit biases of both modalities in ways that make biases more pervasive and difficult to mitigate. Our study explores how VLMs perpetuate homogeneity bias and trait associations with regards to race and gender. When prompted to write stories based on images of human faces, GPT-4V describes subordinate racial and gender groups with greater homogeneity than dominant groups and relies on distinct, yet generally positive, stereotypes. Importantly, VLM stereotyping is driven by visual cues rather than group membership alone such that faces that are rated as more prototypically Black and feminine are subject to greater stereotyping. These findings suggest that VLMs may associate subtle visual cues related to racial and gender groups with stereotypes in ways that could be challenging to mitigate. We explore the underlying reasons behind this behavior and discuss its implications and emphasize the importance of addressing these biases as VLMs come to mirror human perception.