Do VLMs Have a Moral Backbone? A Study on the Fragile Morality of Vision-Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Liu, Zhining, Wang, Tianyi, Lin, Xiao, Ouyang, Penghao, Li, Gaotang, Yang, Ze, Liu, Hui, Keswani, Sumit, Pardeshi, Vishwa, Zhao, Huijun, Fan, Wei, Tong, Hanghang
Format:	Preprint
Published:	2026
Subjects:	Computers and Society Artificial Intelligence Computation and Language Computer Vision and Pattern Recognition Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2601.17082