Safety
Cross-Cultural Value Awareness in Large Vision-Language Models
arXiv:2604.09945v1 Announce Type: cross Abstract: The rapid adoption of large vision-language models (LVLMs) in recent years has been accompanied by growing fairness concerns due to their propensity t
arXiv:2604.09945v1 Announce Type: cross Abstract: The rapid adoption of large vision-language models (LVLMs) in recent years has been accompanied by growing fairness concerns due to their propensity to reinforce harmful societal stereotypes. While significant attention has been paid to such fairness concerns in the context of social biases, relatively little prior work has examined the presence of stereotypes in LVLMs related to cultural contexts such as religion, nationality, and socioeconomic status. In this work, we aim to narrow this gap by investigating how cultural contexts depicted in images influence the judgments LVLMs make about a person's moral, ethical, and political values. We conduct a multi-dimensional analysis of such value judgments in five popular LVLMs using counterfactual image sets, which depict the same person across different cultural contexts. Our evaluation framework diagnoses LVLM awareness of cultural value differences through the use of Moral Foundations Theory, lexical analyses, and the sensitivity of generated values to depicted cultural contexts.
Related
- Risk Awareness Injection: Calibrating Vision-Language Models for Safety without Compromising Utility
- Dictionary-Aligned Concept Control for Safeguarding Multimodal LLMs
- Leave My Images Alone: Preventing Multi-Modal Large Language Models from Analyzing Images via Visual Prompt Injection
- Harnessing Hyperbolic Geometry for Harmful Prompt Detection and Sanitization
- Enhancing the Safety of Medical Vision-Language Models by Synthetic Demonstrations
Source: arXiv cs.AI | 2026-04-14