The State of Multilingual LLM Safety Research: From Measuring the Language Gap to Mitigating It
This work highlights a critical inclusivity problem in AI safety for global populations, though it is incremental as it builds on existing survey methods.
The paper analyzed the linguistic diversity in LLM safety research, finding a significant English-centric gap with minimal attention to non-English languages, and proposed future directions to address this issue.
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.