SEA-Guard：面向东南亚的文化根基多语言安全防护
SEA-Guard: Culturally Grounded Multilingual Safeguard for Southeast Asia
AI总结：
SEA-Guard是首个基于东南亚文化背景的多语言安全模型，通过代理数据生成框架构建区域特定安全数据集，有效检测地区敏感内容并保持良好的通用安全性能。
摘要：
文化意识的安全保障对于现实世界中的AI对齐至关重要，其中安全不仅超越常识，还涵盖多样化的本地价值观、规范和地区特定法规。然而，由于资源有限和本地标注者的稀缺，构建大规模、文化扎根的数据集具有挑战性。因此，许多安全模型依赖于英语数据集的机器翻译，往往忽略了地区和文化细微差别。我们提出了一种新的代理数据生成框架，以可扩展的方式创建真实、地区特定的安全数据集，用于东南亚（SEA）。在此基础上，我们引入了SEA-Guard家族，这是首个基于SEA文化背景的多语言安全模型。在多个基准和文化变体上评估，SEA-Guard在检测地区敏感或有害内容方面始终优于现有安全措施，同时保持了强大的通用安全性能。
英文摘要：
Culturally aware safeguards are crucial for AI alignment in real-world settings, where safety extends beyond common sense and encompasses diverse local values, norms, and region-specific regulations. However, building large-scale, culturally grounded datasets is challenging due to limited resources and a scarcity of native annotators. Consequently, many safeguard models rely on machine translation of English datasets, often missing regional and cultural nuances. We present a novel agentic data-generation framework to scalably create authentic, region-specific safety datasets for Southeast Asia (SEA). On this foundation, we introduce the SEA-Guard family, the first multilingual safeguard models grounded in SEA cultural contexts. Evaluated across multiple benchmarks and cultural variants, SEA-Guard consistently outperforms existing safeguards at detecting regionally sensitive or harmful content while maintaining strong general safety performance.
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。
