The State of Multilingual LLM Safety Research: From Measuring the Language Gap to Mitigating It

TL;DR

This paper analyzes the linguistic diversity in LLM safety research, revealing an English-centric bias, and proposes future directions to improve multilingual safety evaluation, data generation, and crosslingual generalization.

Contribution

It provides the first comprehensive review of multilingual safety research, highlighting gaps and proposing concrete future research directions for more inclusive AI safety.

Findings

English safety research dominates the field.

Non-English languages are rarely studied independently.

There is minimal focus on multilingual safety evaluation.

Abstract

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.