SEA-SafeguardBench: 评估SEA语言和文化中的AI安全
SEA-SafeguardBench: Evaluating AI Safety in SEA Languages and Cultures
AI总结：
SEA-SafeguardBench是首个针对东南亚语言和文化的AI安全评估基准，通过八种语言21640个样本验证LLMs在文化特定危害场景下的表现。
摘要：
安全模型帮助大语言模型（LLMs）检测并阻止有害内容，但大多数评估仍然以英语为中心，并忽视语言和文化多样性。现有的多语言安全基准往往依赖于机器翻译的英语数据，这无法捕捉低资源语言的细微差别。东南亚（SEA）语言尽管该地区语言多样且有独特的安全问题，如文化敏感的政治言论和地区特定的虚假信息，仍被低估。解决这些差距需要反映当地规范和危害场景的原生基准。我们介绍了SEA-SafeguardBench，这是首个针对SEA的人工验证安全基准，涵盖八种语言、21640个样本，分为三个子集：通用、真实世界和内容生成。我们的基准实验结果表明，即使是最先进的LLMs和防护措施也面临SEA文化和危害场景的挑战，并在与英语文本相比时表现欠佳。
英文摘要：
Safeguard models help large language models (LLMs) detect and block harmful content, but most evaluations remain English-centric and overlook linguistic and cultural diversity. Existing multilingual safety benchmarks often rely on machine-translated English data, which fails to capture nuances in low-resource languages. Southeast Asian (SEA) languages are underrepresented despite the region's linguistic diversity and unique safety concerns, from culturally sensitive political speech to region-specific misinformation. Addressing these gaps requires benchmarks that are natively authored to reflect local norms and harm scenarios. We introduce SEA-SafeguardBench, the first human-verified safety benchmark for SEA, covering eight languages, 21,640 samples, across three subsets: general, in-the-wild, and content generation. The experimental results from our benchmark demonstrate that even state-of-the-art LLMs and guardrails are challenged by SEA cultural and harm scenarios and underperform when compared to English texts.
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。
