视觉-语言模型是否具有道德基础？对视觉语言模型脆弱道德的研究
Do VLMs Have a Moral Backbone? A Study on the Fragile Morality of Vision-Language Models
AI总结：
研究发现视觉语言模型在面对文本和视觉扰动时道德判断易变，需通过轻量干预提升道德鲁棒性以确保负责任的部署。
摘要：
尽管在提高视觉语言模型（VLMs）道德对齐方面做出了大量努力，但仍不清楚它们在现实环境中的伦理判断是否稳定。本文研究了VLMs的道德鲁棒性，定义为在不改变底层道德情境的文本和视觉扰动下保持道德判断的能力。我们系统地用一组模型无关的多模态扰动探测VLMs，并发现其道德立场高度脆弱，经常在简单的操纵下翻转。我们的分析揭示了扰动类型、道德领域和模型规模之间的系统性漏洞，包括一种阿谀奉承的权衡，即更强的指令遵循模型更容易受到说服。我们进一步表明，轻量级的推理时间干预可以部分恢复道德稳定性。这些结果表明，仅靠道德对齐是不够的，道德鲁棒性是负责任部署VLMs的必要条件。
英文摘要：
Despite substantial efforts toward improving the moral alignment of Vision-Language Models (VLMs), it remains unclear whether their ethical judgments are stable in realistic settings. This work studies moral robustness in VLMs, defined as the ability to preserve moral judgments under textual and visual perturbations that do not alter the underlying moral context. We systematically probe VLMs with a diverse set of model-agnostic multimodal perturbations and find that their moral stances are highly fragile, frequently flipping under simple manipulations. Our analysis reveals systematic vulnerabilities across perturbation types, moral domains, and model scales, including a sycophancy trade-off where stronger instruction-following models are more susceptible to persuasion. We further show that lightweight inference-time interventions can partially restore moral stability. These results demonstrate that moral alignment alone is insufficient and that moral robustness is a necessary criterion for the responsible deployment of VLMs.
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。
