迷失在翻译中？复合危害的跨语言迁移比较研究
Lost in Translation? A Comparative Study on the Cross-Lingual Transfer of Composite Harms
AI总结：
本研究通过复合危害基准测试，探讨了跨语言迁移中安全对齐的稳定性，发现攻击成功率在印度语言中显著上升，但上下文性危害迁移较温和，强调翻译基准在多语言安全测试中的必要性。
摘要：
大多数大型语言模型的安全评估仍然以英语为基础。翻译常被用作探测多语言行为的快捷方式，但很少能全面反映情况，尤其是当有害意图或结构在不同语言中发生变化时。某些类型的危害在翻译中几乎保持不变，而其他则会扭曲或消失。为研究这种影响，我们引入了CompositeHarm，一个基于翻译的基准测试，旨在检验安全对齐在语法和语义变化时的稳定性。它结合了两个互补的英语数据集，AttaQ，旨在针对结构化对抗攻击，和MMSafetyBench，涵盖上下文性和现实世界的危害，并将其扩展到六种语言：英语、印地语、阿萨姆语、马拉地语、卡纳达语和古吉拉特语。使用三个大型模型，我们发现攻击成功率在印度语言中显著上升，尤其是在对抗性语法下，而上下文性危害的迁移则较为温和。为了确保可扩展性和能源效率，我们的研究采用了受边缘AI设计原则启发的轻量级推理策略，减少冗余评估过程的同时保持跨语言的准确性。这种设计使大规模多语言安全测试在计算上可行且环境友好。总体而言，我们的结果表明，翻译基准是构建基于资源的、语言适应的安全系统的重要第一步，但并非充分条件。
英文摘要：
Most safety evaluations of large language models (LLMs) remain anchored in English. Translation is often used as a shortcut to probe multilingual behavior, but it rarely captures the full picture, especially when harmful intent or structure morphs across languages. Some types of harm survive translation almost intact, while others distort or disappear. To study this effect, we introduce CompositeHarm, a translation-based benchmark designed to examine how safety alignment holds up as both syntax and semantics shift. It combines two complementary English datasets, AttaQ, which targets structured adversarial attacks, and MMSafetyBench, which covers contextual, real-world harms, and extends them into six languages: English, Hindi, Assamese, Marathi, Kannada, and Gujarati. Using three large models, we find that attack success rates rise sharply in Indic languages, especially under adversarial syntax, while contextual harms transfer more moderately. To ensure scalability and energy efficiency, our study adopts lightweight inference strategies inspired by edge-AI design principles, reducing redundant evaluation passes while preserving cross-lingual fidelity. This design makes large-scale multilingual safety testing both computationally feasible and environmentally conscious. Overall, our results show that translated benchmarks are a necessary first step, but not a sufficient one, toward building grounded, resource-aware, language-adaptive safety systems.
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。
