# Towards Safe Multilingual Frontier AI

arXiv: https://arxiv.org/abs/2409.13708 · HTML: https://mlsanity.com/paper/2409.13708/

## Key facts

- Cited by 2 papers in the map (data through 7 Oct 2026).
- Placed in Jailbreaking, one of 12 directions in LLM safety and security.
- Builds on 23 of its 53 references that are in the map.
- First posted on arXiv 6 Sep 2024.

## Placed in

- LLM safety and security / [Jailbreaking](https://mlsanity.com/safety/jailbreaking/)

## Builds on (most cited first, 23 of 23)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [The State and Fate of Linguistic Diversity and Inclusion in the NLP World](https://mlsanity.com/paper/2004.09095/) (2020)
- [A Comprehensive Overview of Large Language Models](https://mlsanity.com/paper/2307.06435/) (2023)
- [Jailbreaking ChatGPT via Prompt Engineering: An Empirical Study](https://mlsanity.com/paper/2305.13860/) (2023)
- [Multilingual Jailbreak Challenges in Large Language Models](https://mlsanity.com/paper/2310.06474/) (2023)
- [OR-Bench: An Over-Refusal Benchmark for Large Language Models](https://mlsanity.com/paper/2405.20947/) (2024)
- [ChatGPT Beyond English: Towards a Comprehensive Evaluation of Large Language Models in Multilingual Learning](https://mlsanity.com/paper/2304.05613/) (2023)
- [Foundational Challenges in Assuring Alignment and Safety of Large Language Models](https://mlsanity.com/paper/2404.09932/) (2024)
- [Survey of Vulnerabilities in Large Language Models Revealed by Adversarial Attacks](https://mlsanity.com/paper/2310.10844/) (2023)
- [Do All Languages Cost the Same? Tokenization in the Era of Commercial Language Models](https://mlsanity.com/paper/2305.13707/) (2023)
- [Language-Specific Neurons: The Key to Multilingual Capabilities in Large Language Models](https://mlsanity.com/paper/2402.16438/) (2024)
- [Black-Box Access is Insufficient for Rigorous AI Audits](https://mlsanity.com/paper/2401.14446/) (2024)
- [The Language Barrier: Dissecting Safety Challenges of LLMs in Multilingual Contexts](https://mlsanity.com/paper/2401.13136/) (2024)
- [A Survey on Multilingual Large Language Models: Corpora, Alignment, and Bias](https://mlsanity.com/paper/2404.00929/) (2024)
- [FP8-LM: Training FP8 Large Language Models](https://mlsanity.com/paper/2310.18313/) (2023)
- [The Multilingual Alignment Prism: Aligning Global and Local Preferences to Reduce Harm](https://mlsanity.com/paper/2406.18682/) (2024)
- [All Languages Matter: On the Multilingual Safety of Large Language Models](https://mlsanity.com/paper/2310.00905/) (2023)
- [A Survey on Large Language Models with Multilingualism: Recent Advances and New Frontiers](https://mlsanity.com/paper/2405.10936/) (2024)
- [A Cross-Language Investigation into Jailbreak Attacks in Large Language Models](https://mlsanity.com/paper/2401.16765/) (2024)
- [Democratising AI: Multiple Meanings, Goals, and Methods](https://mlsanity.com/paper/2303.12642/) (2023)
- [LINGOLY: A Benchmark of Olympiad-Level Linguistic Reasoning Puzzles in Low-Resource and Extinct Languages](https://mlsanity.com/paper/2406.06196/) (2024)
- [Towards Publicly Accountable Frontier LLMs: Building an External Scrutiny Ecosystem under the ASPIRE Framework](https://mlsanity.com/paper/2311.14711/) (2023)

## Built on by (most cited first, 2 of 2)

- [The State of Multilingual LLM Safety Research: From Measuring the Language Gap to Mitigating It](https://mlsanity.com/paper/2505.24119/) (2025)
- [Tiny Aya: Bridging Scale and Multilingual Depth](https://mlsanity.com/paper/2603.11510/) (2026)

## Abstract (arXiv)

Linguistically inclusive LLMs -- which maintain good performance regardless of the language with which they are prompted -- are necessary for the diffusion of AI benefits around the world. Multilingual jailbreaks that rely on language translation to evade safety measures undermine the safe and inclusive deployment of AI systems. We provide policy recommendations to enhance the multilingual capabilities of AI while mitigating the risks of multilingual jailbreaks. We examine how a language's level of resourcing relates to how vulnerable LLMs are to multilingual jailbreaks in that language. We do this by testing five advanced AI models across 24 official languages of the EU. Building on prior research, we propose policy actions that align with the EU legal landscape and institutional framework to address multilingual jailbreaks, while promoting linguistic inclusivity. These include mandatory assessments of multilingual capabilities and vulnerabilities, public opinion research, and state support for multilingual AI development. The measures aim to improve AI safety and functionality through EU policy initiatives, guiding the implementation of the EU AI Act and informing regulatory efforts of the European AI Office.