揭示大模型安全研究的英语霸权，呼吁多语言包容性改进
The State of Multilingual LLM Safety Research: From Measuring the Language Gap to Mitigating It
- 系统分析近300篇论文，发现安全研究严重偏向英语
- 高资源非英语语言也极少被单独研究，存在明显语言鸿沟
- 提出评估、数据生成等3个未来方向，推动跨语言安全研究
本文对2020至2024年间ACL等主要NLP会议近300篇论文进行了系统回顾，揭示大模型安全研究高度英语中心化。研究发现，即使在高资源非英语语言中，安全研究也极为有限，且非英语语言很少作为独立语言被研究。此外，英语安全研究普遍存在语言标注不充分的问题。基于此，本文提出多项建议，并明确三个未来方向：安全评估、训练数据生成和跨语言安全泛化。这些工作旨在推动全球多元语言群体更稳健、更具包容性的AI安全实践。
原文摘要 · Abstract (English)
This paper presents a comprehensive analysis of the linguistic diversity of LLM safety research, highlighting the English-centric nature of the field. Through a systematic review of nearly 300 publications from 2020--2024 across major NLP conferences and workshops at *ACL, we identify a significant and growing language gap in LLM safety research, with even high-resource non-English languages receiving minimal attention. We further observe that non-English languages are rarely studied as a standalone language and that English safety research exhibits poor language documentation practice. To motivate future research into multilingual safety, we make several recommendations based on our survey, and we then pose three concrete future directions on safety evaluation, training data generation, and crosslingual safety generalization. Based on our survey and proposed directions, the field can develop more robust, inclusive AI safety practices for diverse global populations.
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。