Image de couverture de livre

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

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Howard, Phillip, Fraser, Kathleen C., Bhiwandiwalla, Anahita, Kiritchenko, Svetlana
Format:	Preprint
Publié:	2024
Sujets:	Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Uncovering Bias in Large Vision-Language Models with Counterfactuals
par: Howard, Phillip, et autres
Publié: (2024)

Examining Gender and Racial Bias in Large Vision-Language Models Using a Novel Dataset of Parallel Images
par: Fraser, Kathleen C., et autres
Publié: (2024)

Cultural Counterfactuals: Evaluating Cultural Biases in Large Vision-Language Models with Counterfactual Examples
par: Howard, Phillip, et autres
Publié: (2026)

SocialCounterfactuals: Probing and Mitigating Intersectional Social Biases in Vision-Language Models with Counterfactual Examples
par: Howard, Phillip, et autres
Publié: (2023)

Cross-Cultural Value Awareness in Large Vision-Language Models
par: Howard, Phillip, et autres
Publié: (2026)

LVLM-Compress-Bench: Benchmarking the Broader Impact of Large Vision-Language Model Compression
par: Kundu, Souvik, et autres
Publié: (2025)

LVLM-Interpret: An Interpretability Tool for Large Vision-Language Models
par: Stan, Gabriela Ben Melech, et autres
Publié: (2024)

Why do LLaVA Vision-Language Models Reply to Images in English?
par: Hinck, Musashi, et autres
Publié: (2024)

GenderBias-\emph{VL}: Benchmarking Gender Bias in Vision Language Models via Counterfactual Probing
par: Xiao, Yisong, et autres
Publié: (2024)

Cultural Awareness in Vision-Language Models: A Cross-Country Exploration
par: Madasu, Avinash, et autres
Publié: (2025)

Debiasing Large Vision-Language Models by Ablating Protected Attribute Representations
par: Ratzlaff, Neale, et autres
Publié: (2024)

Uncovering Cultural Representation Disparities in Vision-Language Models
par: Kadiyala, Ram Mohan Rao, et autres
Publié: (2025)

Chartographer: Counterfactual Chart Generation for Evaluating Vision-Language Models
par: Jiang, Yifan, et autres
Publié: (2026)

Benchmarking and Mitigating MCQA Selection Bias of Large Vision-Language Models
par: Atabuzzaman, Md., et autres
Publié: (2025)

Measuring Social Bias in Vision-Language Models with Face-Only Counterfactuals from Real Photos
par: Chen, Haodong, et autres
Publié: (2026)

Beyond the Vision Encoder: Identifying and Mitigating Spatial Bias in Large Vision-Language Models
par: Zhu, Yingjie, et autres
Publié: (2025)

Pruning the Paradox: How CLIP's Most Informative Heads Enhance Performance While Amplifying Bias
par: Madasu, Avinash, et autres
Publié: (2025)

Pathological Truth Bias in Vision-Language Models
par: Thube, Yash
Publié: (2025)

Does Acceleration Cause Hidden Instability in Vision Language Models? Uncovering Instance-Level Divergence Through a Large-Scale Empirical Study
par: Sun, Yizheng, et autres
Publié: (2025)

The Bias of Harmful Label Associations in Vision-Language Models
par: Hazirbas, Caner, et autres
Publié: (2024)

Counterfactual Vision-and-Language Navigation via Adversarial Path Sampling
par: Fu, Tsu-Jui, et autres
Publié: (2019)

Image Safeguarding: Reasoning with Conditional Vision Language Model and Obfuscating Unsafe Content Counterfactually
par: Bethany, Mazal, et autres
Publié: (2024)

Behind the Screens: Uncovering Bias in AI-Driven Video Interview Assessments Using Counterfactuals
par: Mujtaba, Dena F., et autres
Publié: (2025)

Uncovering and Shaping the Latent Representation of 3D Scene Topology in Vision-Language Models
par: Wang, Haoming, et autres
Publié: (2026)

Egocentric Bias in Vision-Language Models
par: Wang, Maijunxian, et autres
Publié: (2026)

Scale Can't Overcome Pragmatics: The Impact of Reporting Bias on Vision-Language Reasoning
par: Kamath, Amita, et autres
Publié: (2026)

Seeing Isn't Believing: Uncovering Blind Spots in Evaluator Vision-Language Models
par: Khan, Mohammed Safi Ur Rahman, et autres
Publié: (2026)

Investigating Spatial Attention Bias in Vision-Language Models
par: Chaudhary, Aryan, et autres
Publié: (2025)

Identifying and Mitigating Position Bias of Multi-image Vision-Language Models
par: Tian, Xinyu, et autres
Publié: (2025)

Explanation-Driven Counterfactual Testing for Faithfulness in Vision-Language Model Explanations
par: Ding, Sihao, et autres
Publié: (2025)

GS-Bias: Global-Spatial Bias Learner for Single-Image Test-Time Adaptation of Vision-Language Models
par: Huang, Zhaohong, et autres
Publié: (2025)

C-CoT: Counterfactual Chain-of-Thought with Vision-Language Models for Safe Autonomous Driving
par: Tian, Kefei, et autres
Publié: (2026)

debiaSAE: Benchmarking and Mitigating Vision-Language Model Bias
par: Sasse, Kuleen, et autres
Publié: (2024)

Towards Mitigating Modality Bias in Vision-Language Models for Temporal Action Localization
par: Li, Jiaqi, et autres
Publié: (2026)

Logical Closed Loop: Uncovering Object Hallucinations in Large Vision-Language Models
par: Wu, Junfei, et autres
Publié: (2024)

VLBiasBench: A Comprehensive Benchmark for Evaluating Bias in Large Vision-Language Model
par: Wang, Sibo, et autres
Publié: (2024)

VLFeedback: A Large-Scale AI Feedback Dataset for Large Vision-Language Models Alignment
par: Li, Lei, et autres
Publié: (2024)

Personalized Large Vision-Language Models
par: Pham, Chau, et autres
Publié: (2024)

Joint Vision-Language Social Bias Removal for CLIP
par: Zhang, Haoyu, et autres
Publié: (2024)

Uncovering Brain-Like Hierarchical Patterns in Vision-Language Models through fMRI-Based Neural Encoding
par: Ren, Yudan, et autres
Publié: (2025)