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

arXiv: https://arxiv.org/abs/2505.24119 · HTML: https://mlsanity.com/paper/2505.24119/

## Key facts

- Cited by 45 papers in the map (data through 14 Oct 2026).
- Placed in Safety alignment, refusal and guardrails, one of 12 directions in LLM safety and security.
- Builds on 88 of its 141 references that are in the map.
- First posted on arXiv 30 May 2025.

## Placed in

- LLM safety and security / [Safety alignment, refusal and guardrails](https://mlsanity.com/safety/safety-alignment-refusal-and-guardrails/)

## Builds on (most cited first, 30 of 88)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [Large Language Models Encode Clinical Knowledge](https://mlsanity.com/paper/2212.13138/) (2022)
- [PaLM 2 Technical Report](https://mlsanity.com/paper/2305.10403/) (2023)
- [The State and Fate of Linguistic Diversity and Inclusion in the NLP World](https://mlsanity.com/paper/2004.09095/) (2020)
- [How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs](https://mlsanity.com/paper/2401.06373/) (2024)
- [Studying Large Language Model Generalization with Influence Functions](https://mlsanity.com/paper/2308.03296/) (2023)
- [Low-Resource Languages Jailbreak GPT-4](https://mlsanity.com/paper/2310.02446/) (2023)
- [Deliberative Alignment: Reasoning Enables Safer Language Models](https://mlsanity.com/paper/2412.16339/) (2024)
- [Aya Model: An Instruction Finetuned Open-Access Multilingual Language Model](https://mlsanity.com/paper/2402.07827/) (2024)
- [R-Judge: Benchmarking Safety Risk Awareness for LLM Agents](https://mlsanity.com/paper/2401.10019/) (2024)
- [Multilingual Jailbreak Challenges in Large Language Models](https://mlsanity.com/paper/2310.06474/) (2023)
- [Rainbow Teaming: Open-Ended Generation of Diverse Adversarial Prompts](https://mlsanity.com/paper/2402.16822/) (2024)
- [Foundational Challenges in Assuring Alignment and Safety of Large Language Models](https://mlsanity.com/paper/2404.09932/) (2024)
- [Cultural Bias and Cultural Alignment of Large Language Models](https://mlsanity.com/paper/2311.14096/) (2023)
- [The PRISM Alignment Dataset: What Participatory, Representative and Individualised Human Feedback Reveals About the Subjective and Multicultural Alignment of Large Language Models](https://mlsanity.com/paper/2404.16019/) (2024)
- [Attacks, Defenses and Evaluations for LLM Conversation Safety: A Survey](https://mlsanity.com/paper/2402.09283/) (2024)
- [Hallucinations in Large Multilingual Translation Models](https://mlsanity.com/paper/2303.16104/) (2023)
- [Large language models in healthcare and medical domain: A review](https://mlsanity.com/paper/2401.06775/) (2023)
- [Simulating Classroom Education with LLM-Empowered Agents](https://mlsanity.com/paper/2406.19226/) (2024)
- [Beyond One-Preference-Fits-All Alignment: Multi-Objective Direct Preference Optimization](https://mlsanity.com/paper/2310.03708/) (2023)
- [Systematic Inequalities in Language Technology Performance across the World's Languages](https://mlsanity.com/paper/2110.06733/) (2021)
- [Gender Bias in Machine Translation](https://mlsanity.com/paper/2104.06001/) (2021)
- [Self-Distillation Bridges Distribution Gap in Language Model Fine-Tuning](https://mlsanity.com/paper/2402.13669/) (2024)
- [The Language Barrier: Dissecting Safety Challenges of LLMs in Multilingual Contexts](https://mlsanity.com/paper/2401.13136/) (2024)
- [Language Contamination Helps Explain the Cross-lingual Capabilities of English Pretrained Models](https://mlsanity.com/paper/2204.08110/) (2022)
- [BLOOM+1: Adding Language Support to BLOOM for Zero-Shot Prompting](https://mlsanity.com/paper/2212.09535/) (2022)
- [SafetyPrompts: a Systematic Review of Open Datasets for Evaluating and Improving Large Language Model Safety](https://mlsanity.com/paper/2404.05399/) (2024)
- [Clio: Privacy-Preserving Insights into Real-World AI Use](https://mlsanity.com/paper/2412.13678/) (2024)

## Built on by (most cited first, 30 of 45)

- [Tiny Aya: Bridging Scale and Multilingual Depth](https://mlsanity.com/paper/2603.11510/) (2026)
- [Self-Jailbreaking: Language Models Can Reason Themselves Out of Safety Alignment After Benign Reasoning Training](https://mlsanity.com/paper/2510.20956/) (2025)
- [Safe Language Generation in the Limit](https://mlsanity.com/paper/2601.08648/) (2026)
- [Align Once, Benefit Multilingually: Enforcing Multilingual Consistency for LLM Safety Alignment](https://mlsanity.com/paper/2602.16660/) (2026)
- [Response-Based Knowledge Distillation for Multilingual Jailbreak Prevention Unwittingly Compromises Safety](https://mlsanity.com/paper/2602.11157/) (2025)
- [LASA: Language-Agnostic Semantic Alignment at the Semantic Bottleneck for LLM Safety](https://mlsanity.com/paper/2604.12710/) (2026)
- [Multilingual Safety Alignment via Self-Distillation](https://mlsanity.com/paper/2605.02971/) (2026)
- [Mina: A Multilingual LLM-Powered Legal Assistant Agent for Bangladesh for Empowering Access to Justice](https://mlsanity.com/paper/2511.08605/) (2025)
- [XL-SafetyBench: A Country-Grounded Cross-Cultural Benchmark for LLM Safety and Cultural Sensitivity](https://mlsanity.com/paper/2605.05662/) (2026)
- [Low-Resource Safety Failures Are Action Failures, Not Representation Failures](https://mlsanity.com/paper/2606.01196/) (2026)
- [Multilingual Refusal Alignment for Safer Large Language Models](https://mlsanity.com/paper/2606.07535/) (2026)
- [The Culture Funnel: You Can't Align What isn't in the Data](https://mlsanity.com/paper/2606.13808/) (2026)
- [Policy-Grounded Safety Evaluation of 20 Large Language Models](https://mlsanity.com/paper/2507.14719/) (2025)
- [The Problem with Safety Classification is not just the Models](https://mlsanity.com/paper/2507.21782/) (2025)
- [BengaliMoralBench: A Benchmark for Auditing Moral Reasoning in Large Language Models within Bengali Language and Culture](https://mlsanity.com/paper/2511.03180/) (2025)
- [JMedEthicBench: A Multi-Turn Conversational Benchmark for Evaluating Medical Safety in Japanese Large Language Models](https://mlsanity.com/paper/2601.01627/) (2026)
- [Alignment Backfire: Language-Dependent Reversal of Safety Interventions Across 16 Languages in LLM Multi-Agent Systems](https://mlsanity.com/paper/2603.04904/) (2026)
- [Multilinguality at the Edge: Developing Language Models for the Global South](https://mlsanity.com/paper/2604.21637/) (2026)
- [Multilingual jailbreaking of LLMs using low-resource languages](https://mlsanity.com/paper/2605.18239/) (2026)
- [AlbanianLLMSafety: A Safety Evaluation Dataset for Large Language Models in Albanian](https://mlsanity.com/paper/2605.26954/) (2026)
- [The Illusion of Cross-Lingual Safety in Low-Resource Languages](https://mlsanity.com/paper/2608.11146/) (2026)
- [Mirror, Mirror on the Wall -- Which is the Best Model of Them All?](https://mlsanity.com/paper/2512.02043/) (2025)
- [Taiwan Safety Benchmark and Breeze Guard: Toward Trustworthy AI for Taiwanese Mandarin](https://mlsanity.com/paper/2603.07286/) (2026)
- [BIASEDTALES-ML: A Multilingual Dataset for Analyzing Narrative Attribute Distributions in LLM-Generated Stories](https://mlsanity.com/paper/2604.17008/) (2026)
- [Cross-Lingual Jailbreak Detection via Semantic Codebooks](https://mlsanity.com/paper/2604.25716/) (2026)
- [Lost in the Tower of Babel: The Adverse Effects of Incidental Multilingualism in LLMs](https://mlsanity.com/paper/2605.01224/) (2026)
- [ROK-FORTRESS: Measuring the Effect of Geopolitical Transcreation for National Security and Public Safety](https://mlsanity.com/paper/2605.14152/) (2026)
- [SomaliBench Eval: Measuring English-to-Somali Refusal Gaps in Open-Weight Language Models](https://mlsanity.com/paper/2605.25420/) (2026)
- [Beyond English and Evasion: A Human-Annotated Multi-Domain Benchmark for High-Stakes LLM Safety Evaluation in Chinese](https://mlsanity.com/paper/2605.29667/) (2026)
- [RiskNet: A large-scale dataset of AI risk incidents from news with alignment and multi-dimensional annotations](https://mlsanity.com/paper/2606.08376/) (2026)

## Abstract (arXiv)

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.