arXiv AI
Mitigating Bias in Large Vision-Language Models via Counterfactual Ensemble Decoding
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
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.
arXiv AI
Jul 24
Unlearning Under Imbalance: Benchmarking Fairness in Multimodal LLM Unlearning
arXiv:2607. 21300v1 Announce Type: cross Abstract: Machine unlearning has emerged as a tool for removing personal data from trained models to comply with recent AI regulations.
arXiv AI
1d ago
BiasGym: A Simple and Generalizable Framework for Analyzing and Removing Biases through Injection
arXiv:2508.08855v5 Announce Type: replace-cross Abstract: Understanding biases and stereotypes encoded in the weights of Large Language Models (LLMs) is crucial for developing effective mitigation st...
arXiv Computer Vision
2d ago
Guardrail-Agnostic Societal Bias Evaluation in Large Vision-Language Models
arXiv:2608.29590v1 Announce Type: new Abstract: We propose a societal bias evaluation method for large vision-language models (LVLMs) in the era of strong safety guardrails. Existing benchmarks rely...
arXiv AI
Jun 18
When Cars Have Stereotypes: Auditing Demographic Bias in Objects from Text-to-Image Models
arXiv:2508. 03483v3 Announce Type: replace-cross Abstract: While prior research on text-to-image generation has predominantly focused on biases in human depictions, demographic bias in generated objects remains relatively underexplored.
arXiv AI
Jun 24
When Language Overwrites Vision: Over-Alignment and Geometric Debiasing in Vision-Language Models
arXiv:2605. 08245v4 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) increasingly power high-stakes applications, from medical imaging to autonomous systems, yet they routinely hallucinate, confidently describing content not present in the input.