发表机构
Korea University; Georgia Institute of Technology（高丽大学; 佐治亚理工学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究聚焦安全对齐对不同语言群体的成本差异，提出安全成本衡量协议，发现非英语用户安全成本更高，存在双重惩罚等三种模式，暴露了安全对齐实践的系统性差异。
AI 中文摘要
安全对齐帮助模型遵守人类价值观，但往往会降低响应效用。我们提出一个关键却未被充分研究的问题：安全对齐对不同语言群体的成本是否均等？为解答此问题，我们引入一套严谨的协议来衡量仅由安全对齐带来的效用损失，将其称为安全成本。通过安全对齐模型与其未对齐对应模型的直接成对比较，我们发现了系统性的不公平现象：非英语用户始终比英语用户承担更高的安全成本。我们进一步识别出三种潜在模式：第一，多种语言处于双重惩罚区，既面临更弱的安全保护，又承受更大的效用损失；第二，某些语言出现明显的效用提升，实则是安全过滤器未启动的结果；第三，即便高资源语言要达到同等安全水平，也比英语付出更高的安全成本。我们表明，这些差异源于明确的拒绝和多个维度上的隐性质量差异。通过准确衡量安全对齐的差异化影响，我们的发现揭示了当前安全对齐实践中存在的系统性差异。
英文摘要
Safety alignment helps models adhere to human values, but it often reduces response utility. We ask a critical but understudied question: Does safety alignment impose the cost equally across language groups? To answer this, we introduce a rigorous protocol to measure the utility loss imposed solely by safety alignment, which we term Safety Cost. Through direct pairwise comparisons between safety-aligned models and their unaligned counterparts, we find a systematic inequity: non-English users consistently bear a higher Safety Cost than English users. We further identify three underlying patterns. First, multiple languages lie in a double-penalty zone, experiencing both weaker safety protection and larger utility loss. Second, certain languages exhibit apparent utility gains that are in fact a consequence of safety filters failing to engage. Third, even high-resource languages pay a larger Safety Cost than English to reach the same level of safety. We show that these disparities arise from both explicit refusals and implicit qualitative differences across multiple dimensions. By accurately measuring the disparate effects of safety alignment, our findings expose a systematic disparity in current safety alignment practices.
CommentsAccepted to EMNLP 2026 Main Conference
