Data Matters Most: Auditing Social Bias in Contrastive Vision Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Sahili, Zahraa Al, Patras, Ioannis, Purver, Matthew
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Breaking Language Barriers or Reinforcing Bias? A Study of Gender and Racial Disparities in Multilingual Contrastive Vision Language Models
by: Sahili, Zahraa Al, et al.
Published: (2025)

FairCoT: Enhancing Fairness in Text-to-Image Generation via Chain of Thought Reasoning with Multimodal Large Language Models
by: Sahili, Zahraa Al, et al.
Published: (2024)

Multimodal Machine Learning in Mental Health: A Survey of Data, Algorithms, and Challenges
by: Sahili, Zahraa Al, et al.
Published: (2024)

FairJudge: Abstention-Aware Multimodal Judges for Fairness and Alignment Evaluation in Text-to-Image Models
by: Sahili, Zahraa Al, et al.
Published: (2025)

On the Effectiveness of Membership Inference in Targeted Data Extraction from Large Language Models
by: Sahili, Ali Al, et al.
Published: (2025)

Beyond Linear Probes: Dynamic Safety Monitoring for Language Models
by: Oldfield, James, et al.
Published: (2025)

FALE: Fairness-Aware ALE Plots for Auditing Bias in Subgroups
by: Giannopoulos, Giorgos, et al.
Published: (2024)

AIM-Fair: Advancing Algorithmic Fairness via Selectively Fine-Tuning Biased Models with Contextual Synthetic Data
by: Zhao, Zengqun, et al.
Published: (2025)

SSR: An Efficient and Robust Framework for Learning with Unknown Label Noise
by: Feng, Chen, et al.
Published: (2021)

$\boldsymbolλ$-Orthogonality Regularization for Compatible Representation Learning
by: Ricci, Simone, et al.
Published: (2025)

Efficient Solutions For An Intriguing Failure of LLMs: Long Context Window Does Not Mean LLMs Can Analyze Long Sequences Flawlessly
by: Hosseini, Peyman, et al.
Published: (2024)

Evaluating Fairness in Transaction Fraud Models: Fairness Metrics, Bias Audits, and Challenges
by: Kamalaruban, Parameswaran, et al.
Published: (2024)

Two Effects, One Trigger: On the Modality Gap, Object Bias, and Information Imbalance in Contrastive Vision-Language Models
by: Schrodi, Simon, et al.
Published: (2024)

FairTree: Subgroup Fairness Auditing of Machine Learning Models with Bias-Variance Decomposition
by: Debelak, Rudolf
Published: (2026)

What's in a Name? Auditing Large Language Models for Race and Gender Bias
by: Salinas, Alejandro, et al.
Published: (2024)

Privacy Bias in Language Models: A Contextual Integrity-based Auditing Metric
by: Shvartzshnaider, Yan, et al.
Published: (2024)

Epistemic Error Decomposition for Multi-step Time Series Forecasting: Rethinking Bias-Variance in Recursive and Direct Strategies
by: Green, Riku, et al.
Published: (2025)

Lon-ea at SemEval-2023 Task 11: A Comparison of Activation Functions for Soft and Hard Label Prediction
by: Hosseini, Peyman, et al.
Published: (2023)

Data-Efficient Contrastive Self-supervised Learning: Most Beneficial Examples for Supervised Learning Contribute the Least
by: Joshi, Siddharth, et al.
Published: (2023)

A Regime-Aware Fusion Framework for Time Series Classification
by: Chauhan, Honey Singh, et al.
Published: (2025)

RED CoMETS: An ensemble classifier for symbolically represented multivariate time series
by: Bennett, Luca A., et al.
Published: (2023)

CG-TTRL: Context-Guided Test-Time Reinforcement Learning for On-Device Large Language Models
by: Hosseini, Peyman, et al.
Published: (2025)

Temporal patterns in insulin needs for Type 1 diabetes
by: Degen, Isabella, et al.
Published: (2022)

An Auditing Test To Detect Behavioral Shift in Language Models
by: Richter, Leo, et al.
Published: (2024)

Auditing Algorithmic Bias in Transformer-Based Trading
by: Gerami, Armin, et al.
Published: (2025)

Understanding and Mitigating Tokenization Bias in Language Models
by: Phan, Buu, et al.
Published: (2024)

On the Domain Robustness of Contrastive Vision-Language Models
by: Koddenbrock, Mario, et al.
Published: (2025)

Shapley Neuron Values for Continual Learning: Which Neurons Matter Most?
by: Vahedifar, Mohammad Ali, et al.
Published: (2026)

MMA-MRNNet: Harnessing Multiple Models of Affect and Dynamic Masked RNN for Precise Facial Expression Intensity Estimation
by: Kollias, Dimitrios, et al.
Published: (2023)

Inducing Dyslexia in Vision Language Models
by: Honarmand, Melika, et al.
Published: (2025)

Mostly Text, Smart Visuals: Asymmetric Text-Visual Pruning for Large Vision-Language Models
by: Li, Sijie, et al.
Published: (2026)

Cascading Adversarial Bias from Injection to Distillation in Language Models
by: Chaudhari, Harsh, et al.
Published: (2025)

Towards Interpretability Without Sacrifice: Faithful Dense Layer Decomposition with Mixture of Decoders
by: Oldfield, James, et al.
Published: (2025)

Privacy Auditing of Large Language Models
by: Panda, Ashwinee, et al.
Published: (2025)

An Empirical Study Into What Matters for Calibrating Vision-Language Models
by: Tu, Weijie, et al.
Published: (2024)

Auditing Language Model Unlearning via Information Decomposition
by: Goel, Anmol, et al.
Published: (2026)

Decoupling Augmentation Bias in Prompt Learning for Vision-Language Models
by: Kim, Gahyeon, et al.
Published: (2025)

Subgroups Matter for Robust Bias Mitigation
by: Alloula, Anissa, et al.
Published: (2025)

An Introduction to Vision-Language Modeling
by: Bordes, Florian, et al.
Published: (2024)

Instance-Level Data-Use Auditing of Visual ML Models
by: Huang, Zonghao, et al.
Published: (2025)