视觉干扰削弱了视觉语言模型中的道德推理
Visual Distraction Undermines Moral Reasoning in Vision-Language Models
AI总结:
研究揭示视觉输入会改变视觉语言模型的道德决策,超越文本安全机制,提出多模态基准MDS以分析视觉与上下文变量对道德决策的影响。
摘要:
道德推理对安全人工智能至关重要,但确保其在不同模态间的一致性变得关键,随着AI系统从基于文本的助手发展为具身代理。当前的安全技术在文本环境中表现良好,但对视觉输入的泛化仍存疑虑。现有道德评估基准依赖纯文本格式,缺乏对影响道德决策变量的系统控制。本文显示,视觉输入根本改变了最先进的视觉语言模型(VLMs)的道德决策,绕过了基于文本的安全机制。我们引入道德困境模拟(MDS),一个基于道德基础理论(MFT)的多模态基准,通过正交操控视觉和上下文变量实现机制分析。评估发现,视觉模态激活了类似直觉的路径,这些路径超越了文本环境中观察到的更谨慎和安全的推理模式。这些发现揭示了关键脆弱性,语言调优的安全过滤器无法约束视觉处理,凸显了多模态安全对齐的紧迫需求。
英文摘要:
Moral reasoning is fundamental to safe Artificial Intelligence (AI), yet ensuring its consistency across modalities becomes critical as AI systems evolve from text-based assistants to embodied agents. Current safety techniques demonstrate success in textual contexts, but concerns remain about generalization to visual inputs. Existing moral evaluation benchmarks rely on textonly formats and lack systematic control over variables that influence moral decision-making. Here we show that visual inputs fundamentally alter moral decision-making in state-of-the-art (SOTA) Vision-Language Models (VLMs), bypassing text-based safety mechanisms. We introduce Moral Dilemma Simulation (MDS), a multimodal benchmark grounded in Moral Foundation Theory (MFT) that enables mechanistic analysis through orthogonal manipulation of visual and contextual variables. The evaluation reveals that the vision modality activates intuition-like pathways that override the more deliberate and safer reasoning patterns observed in text-only contexts. These findings expose critical fragilities where language-tuned safety filters fail to constrain visual processing, demonstrating the urgent need for multimodal safety alignment.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。