为南半球语言构建高效文化适配的安全对齐方法
Bridging the Multilingual Safety Divide: Efficient, Culturally-Aware Alignment for Global South Languages
- 提出参数高效安全调优，适配低资源与混合语境
- 发现英语安全机制在非英语场景失效，文化危害仍存
- 倡导本地社区参与，推动公平AI落地
大语言模型正被部署于全球南方地区，日常使用涉及低资源语言、代码混用及文化特异性规范。然而，当前的安全管道、评估基准与对齐方法仍主要针对英语和少数高资源语言，隐含假设安全与事实性可跨语言迁移，但证据表明其并不成立。我们综合最新研究发现：(i) 安全防护在低资源和代码混用输入上显著弱化；(ii) 即使标准毒性评分合格，文化有害行为仍可能持续存在；(iii) 仅基于英语的知识修正与安全补丁难以迁移到低资源语言。为此，我们为全球南方的研究者与学生提出务实路径：参数高效的安全引导、基于文化的评估与偏好数据构建，以及赋能本地社区参与的协作流程。目标是将多语言安全作为代表性不足区域公平AI的核心要求，而非附加项。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。