弥合多语言安全鸿沟：为全球南方语言实现高效、文化感知的对齐
Bridging the Multilingual Safety Divide: Efficient, Culturally-Aware Alignment for Global South Languages
AI总结：
本文提出为全球南方低资源语言提供高效、文化感知的安全对齐方法，以解决现有安全机制在多语言环境中的失效问题。
摘要：
大型语言模型（LLMs）正在被部署到全球南方地区，日常使用涉及低资源语言、混合语言和文化特定规范。然而，安全管道、基准和对齐仍然主要针对英语和少数高资源语言，隐含假设安全性和事实性可以在不同语言之间转移。证据越来越多地表明，这种假设并不成立。我们综合了最近的研究发现，指出（i）安全护栏在低资源和混合输入上急剧减弱，（ii）文化有害行为即使在标准毒性评分看起来可接受时仍可能持续，（iii）仅英语知识编辑和安全补丁往往无法转移到低资源语言。对此，我们为全球南方的研究人员和学生提出一个实用议程：参数高效的安全引导、基于文化的评估和偏好数据，以及赋权当地社区定义和减轻危害的参与工作流。我们的目标是使多语言安全成为公平AI在边缘化地区的核心要求，而非附加功能。
英文摘要：
Large language models (LLMs) are being deployed across the Global South, where everyday use involves low-resource languages, code-mixing, and culturally specific norms. Yet safety pipelines, benchmarks, and alignment still largely target English and a handful of high-resource languages, implicitly assuming safety and factuality ''transfer'' across languages. Evidence increasingly shows they do not. We synthesize recent findings indicating that (i) safety guardrails weaken sharply on low-resource and code-mixed inputs, (ii) culturally harmful behavior can persist even when standard toxicity scores look acceptable, and (iii) English-only knowledge edits and safety patches often fail to carry over to low-resource languages. In response, we outline a practical agenda for researchers and students in the Global South: parameter-efficient safety steering, culturally grounded evaluation and preference data, and participatory workflows that empower local communities to define and mitigate harm. Our aim is to make multilingual safety a core requirement-not an add-on-for equitable AI in underrepresented regions.
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。
