# Vision-Language Models Suppress Female Representations Under Ambiguous Input

arXiv: https://arxiv.org/abs/2605.31556 · HTML: https://mlsanity.com/paper/2605.31556/

## Key facts

- Cited by 1 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 30 of its 48 references that are in the map.
- First posted on arXiv 29 May 2026.

## 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, 30 of 30)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings](https://mlsanity.com/paper/1607.06520/) (2016)
- [Semantics derived automatically from language corpora contain human-like biases](https://mlsanity.com/paper/1608.07187/) (2016)
- [Eliciting Latent Predictions from Transformers with the Tuned Lens](https://mlsanity.com/paper/2303.08112/) (2023)
- [Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraints](https://mlsanity.com/paper/1707.09457/) (2017)
- [On Measuring Social Biases in Sentence Encoders](https://mlsanity.com/paper/1903.10561/) (2019)
- [Lipstick on a Pig: Debiasing Methods Cover up Systematic Gender Biases in Word Embeddings But do not Remove Them](https://mlsanity.com/paper/1903.03862/) (2019)
- [Women also Snowboard: Overcoming Bias in Captioning Models](https://mlsanity.com/paper/1803.09797/) (2018)
- [Patchscopes: A Unifying Framework for Inspecting Hidden Representations of Language Models](https://mlsanity.com/paper/2401.06102/) (2024)
- [Causal Mediation Analysis for Interpreting Neural NLP: The Case of Gender Bias](https://mlsanity.com/paper/2004.12265/) (2020)
- [Detecting Emergent Intersectional Biases: Contextualized Word Embeddings Contain a Distribution of Human-like Biases](https://mlsanity.com/paper/2006.03955/) (2020)
- [Harms of Gender Exclusivity and Challenges in Non-Binary Representation in Language Technologies](https://mlsanity.com/paper/2108.12084/) (2021)
- [Are Gender-Neutral Queries Really Gender-Neutral? Mitigating Gender Bias in Image Search](https://mlsanity.com/paper/2109.05433/) (2021)
- [Vision Language Models are Biased](https://mlsanity.com/paper/2505.23941/) (2025)
- [Examining Gender and Racial Bias in Large Vision-Language Models Using a Novel Dataset of Parallel Images](https://mlsanity.com/paper/2402.05779/) (2024)
- [SocialCounterfactuals: Probing and Mitigating Intersectional Social Biases in Vision-Language Models with Counterfactual Examples](https://mlsanity.com/paper/2312.00825/) (2023)
- [VisoGender: A dataset for benchmarking gender bias in image-text pronoun resolution](https://mlsanity.com/paper/2306.12424/) (2023)
- [Mitigating Gender Bias in Captioning Systems](https://mlsanity.com/paper/2006.08315/) (2020)
- [American == White in Multimodal Language-and-Image AI](https://mlsanity.com/paper/2207.00691/) (2022)
- [GenderBias-VL: Benchmarking Gender Bias in Vision Language Models via Counterfactual Probing](https://mlsanity.com/paper/2407.00600/) (2024)
- [See It from My Perspective: How Language Affects Cultural Bias in Image Understanding](https://mlsanity.com/paper/2406.11665/) (2024)
- [Revealing and Reducing Gender Biases in Vision and Language Assistants (VLAs)](https://mlsanity.com/paper/2410.19314/) (2024)
- [LatentLens: Revealing Highly Interpretable Visual Tokens in LLMs](https://mlsanity.com/paper/2602.00462/) (2026)
- [Images Speak Louder than Words: Understanding and Mitigating Bias in Vision-Language Model from a Causal Mediation Perspective](https://mlsanity.com/paper/2407.02814/) (2024)
- [Interpretable Debiasing of Vision-Language Models for Social Fairness](https://mlsanity.com/paper/2602.24014/) (2026)
- [Vision-Language Models display a strong gender bias](https://mlsanity.com/paper/2508.11262/) (2025)
- [Evaluation of Vision-LLMs in Surveillance Video](https://mlsanity.com/paper/2510.23190/) (2025)

## Built on by (most cited first, 1 of 1)

- [How Humans and LLMs Read Gender into "Gender-Neutral" Physical Descriptions](https://mlsanity.com/paper/2609.16366/) (2026)

## Abstract (arXiv)

Alignment teaches vision-language models (VLMs) to avoid expressing demographic biases, and when gender is clearly visible they largely succeed. Far less is known about ambiguous inputs (a worker in full gear, a figure seen from behind), cases common in practice yet rarely studied. We find that minimal prompting pressure exposes occupation-gender defaults when prompting ambiguous input images, with models collapsing to male even for strongly female-stereotyped occupations. But do these outputs reflect what models actually encode internally? We introduce LALS (Latent Association Leaning Score), a zero-shot metric that projects visual-token activations into the model's text-embedding space to measure concept associations per token and layer. Across 15 occupations, over 800 gender-ambiguous images, and four VLMs, internal representations and outputs often become systematically decoupled: models often encode a female association internally yet output male. Layer-wise analysis reveals an asymmetric filter: male signal amplifies end-to-end while female signal peaks mid-network and is suppressed before generation. A color ablation shows that culturally loaded visual cues such as clothing color further modulate these internal associations.