arXiv Computer Vision

Gender Bias in Vision-Language In-Context Learning

The paper investigates how in‑context learning (ICL) in large vision‑language models (LVLMs) can amplify gender bias. Using the VL‑BICLE framework, the authors show that gendered ICL demonstrations shift model bias toward the demonstrated gender, especially in tasks involving gendered language such as image captioning and pronoun prediction. They find that similarity‑based retrieval does not mitigate this bias and that replacing real images with synthetic ones from stable diffusion reduces bias without hurting caption quality.

arXiv Computer Vision

Sep 16

ViD: Vision-Dominant Gender Bias Mitigation for Large Vision-Language Models

The paper introduces ViD, a vision‑dominant gender bias mitigation framework for large vision‑language models. ViD uses causal analysis of attention patterns and dual mechanisms—backdoor adjustment and refined token selection—to suppress bias while preserving reasoning and generation quality. Experiments show a 14.7% reduction in gender bias on FACET and significant improvements on MS COCO image captioning, all without extra training overhead.

By Zhipeng Zhao, Zhaoqiang Wei, Peishun Liu, Youwei Zhao, Ruichun Tang

llms multimodal benchmarks safety

arXiv AI

Jul 31

BioPro: Towards Difference-Aware Gender Fairness for Vision-Language Models

arXiv:2512. 00807v2 Announce Type: replace Abstract: Vision-Language Models (VLMs) inherit significant social biases from their training data, notably in gender representation.

By Yujie Lin, Jiayao Ma, Qingguo Hu, Wenbo Li, Genji Li, Derek Wong, Jinsong Su

llms rag diffusion multimodal safety

arXiv AI

Sep 1

Vision-Language Models Suppress Female Representations Under Ambiguous Input

arXiv:2605.31556v2 Announce Type: replace-cross Abstract: Alignment teaches vision-language models (VLMs) to avoid expressing demographic biases, and when gender is clearly visible they largely succe...

By Arnau Marin-Llobet, Simon Henniger, Mahzarin R. Banaji

llms rag multimodal benchmarks safety

arXiv AI

Aug 18

DR.GAP: Mitigating Bias in Large Language Models using Gender-Aware Prompting with Decoupled Reasoning

arXiv:2502. 11603v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) exhibit strong natural language understanding capabilities but also inherit and amplify societal biases, particularly gender bias, raising fairness concerns.

By Hongye Qiu, Yue Xu, Yi Wang, Meikang Qiu, Wenjie Wang

llms multimodal safety

arXiv Computation and Language

Sep 11

Alignment Reduces Expressed but Not Encoded Gender Bias: A Unified Framework and Study

The paper introduces a unified framework that simultaneously measures intrinsic (encoded) and extrinsic (expressed) gender bias in large language models using identical neutral prompts. It finds a consistent link between latent gender information and output bias, but shows that alignment via supervised fine‑tuning reduces expressed bias while leaving internal gender associations largely intact and reactivatable by adversarial prompts. The study also demonstrates that debiasing gains on structured benchmarks may not transfer to realistic tasks such as story generation.

By Nour Bouchouchi, Thibault Laugel, Xavier Renard, Christophe Marsala, Marie-Jeanne Lesot, Marcin Detyniecki

llms fine-tuning benchmarks safety

arXiv Computation and Language

Sep 1

ContextBias: Controlled Evaluation of Bias Persistence Under Context Shift in Text-to-Image Models

arXiv:2608.29847v1 Announce Type: cross Abstract: Text-to-image models learn associations between concepts - in the case of this paper, people's professions, which we refer to as roles - and visual a...

By Shaghayegh Kolli, Sina Emami, Moreno D'Inc\`a, Pouyan Nejadi, Nicu Sebe, Massimiliano Mancini, Jana Diesner

diffusion benchmarks safety

Hugging Face Trending Papers

Aug 30

ContextBias: Controlled Evaluation of Bias Persistence Under Context Shift in Text-to-Image Models

Text-to-image models learn associations between concepts - in the case of this paper, people's professions, which we refer to as roles - and visual attributes. These associations can underpin many obs...

diffusion benchmarks safety

arXiv AI

Jun 2

Failure of contextual invariance in large language models

arXiv:2603. 23485v2 Announce Type: replace-cross Abstract: Standard evaluation practices assume that large language model (LLM) outputs are stable when prompts are embedded in contextually equivalent discourses.

By Sagar Kumar, Ariel Flint, Luca Maria Aiello, Andrea Baronchelli

llms benchmarks safety

arXiv AI

Sep 15

Through the Eyes of the Beholder: Biometric and Demographic Conditioning for Multimodal Sexism Detection

arXiv:2609.15608v1 Announce Type: cross Abstract: Detecting sexism on the internet is a fundamentally subjective task; our team, VANGUARD, addresses this challenge in the EXIST 2026 Task 2 by proposi...

By Ana-Maria Luisa Mocanu, Sebastian Mocanu, Ciprian-Octavian Truic\u{a}, Elena-Simona Apostol

multimodal

arXiv Computer Vision

Sep 22

IMPLICIT-Bench: Measuring Implicit Bias in Text-to-Image Models under Neutral Prompts

arXiv:2609.24228v1 Announce Type: new Abstract: Text-to-image (T2I) models are typically evaluated for bias using slot-based templates such as ``a photo of a [profession]''. Such templates probe only...

By Yue Dai, Ziyang Liu, Marc Cheong, Caren Han

diffusion benchmarks safety

arXiv AI

Aug 25

Mitigating Bias in Large Vision-Language Models via Counterfactual Ensemble Decoding

arXiv:2608.21415v1 Announce Type: cross Abstract: Large Vision-Language Models (LVLMs) have achieved remarkable performance across a wide range of tasks; however, they often inherit social biases fro...

By Yisong Xiao, Aishan Liu, Yongxin Huang, Zonghao Ying, Shiji Zhao, Tianlin Li, Yong Han, Jian Yang, Xianglong Liu

llms multimodal benchmarks safety

arXiv Machine Learning

Jun 9

Exposing Hidden Biases in Text-to-Image Models via Automated Prompt Search

arXiv:2512. 08724v3 Announce Type: replace Abstract: Text-to-image (TTI) diffusion models have achieved remarkable visual quality, yet they have been repeatedly shown to exhibit social biases across sensitive attributes such as gender, race and age.

By Manos Plitsis, Giorgos Bouritsas, Vassilis Katsouros, Yannis Panagakis

llms diffusion benchmarks safety

Related stories