Towards Safe Multilingual Frontier AI
On the map: LLM safety and security → Jailbreaking
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.
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.
Builds on
23 of 53 references.
Closest ancestors · 5
Same direction, newest first
- 2024A Cross-Language Investigation into Jailbreak Attacks in Large Language Models30 Jan
- 2023Survey of Vulnerabilities in Large Language Models Revealed by Adversarial Attacks16 Oct
- 2023Multilingual Jailbreak Challenges in Large Language Models10 Oct
- 2023Universal and Transferable Adversarial Attacks on Aligned Language Models27 Jul
- 2023Jailbreaking ChatGPT via Prompt Engineering: An Empirical Study23 May
Other references · 18
- 2024The Llama 3 Herd of Modelscited by 14,192
- 2020The State and Fate of Linguistic Diversity and Inclusion in the NLP Worldcited by 789
- 2023A Comprehensive Overview of Large Language Modelscited by 639
- 2024OR-Bench: An Over-Refusal Benchmark for Large Language Modelscited by 222
- 2023ChatGPT Beyond English: Towards a Comprehensive Evaluation of Large Language Models in Multilingual Learningcited by 203
- 2024Foundational Challenges in Assuring Alignment and Safety of Large Language Modelscited by 193
- 2023Do All Languages Cost the Same? Tokenization in the Era of Commercial Language Modelscited by 186
- 2024Language-Specific Neurons: The Key to Multilingual Capabilities in Large Language Modelscited by 124
- 2024Black-Box Access is Insufficient for Rigorous AI Auditscited by 123
- 2024The Language Barrier: Dissecting Safety Challenges of LLMs in Multilingual Contextscited by 92
- 2024A Survey on Multilingual Large Language Models: Corpora, Alignment, and Biascited by 82
- 2023FP8-LM: Training FP8 Large Language Modelscited by 75
6 more
- 2024The Multilingual Alignment Prism: Aligning Global and Local Preferences to Reduce Harmcited by 67
- 2023All Languages Matter: On the Multilingual Safety of Large Language Modelscited by 51
- 2024A Survey on Large Language Models with Multilingualism: Recent Advances and New Frontierscited by 39
- 2023Democratising AI: Multiple Meanings, Goals, and Methodscited by 29
- 2024LINGOLY: A Benchmark of Olympiad-Level Linguistic Reasoning Puzzles in Low-Resource and Extinct Languagescited by 28
- 2023Towards Publicly Accountable Frontier LLMs: Building an External Scrutiny Ecosystem under the ASPIRE Frameworkcited by 11
Built on by
Citing papers per year: 2025: 1; 2026: 1.
2 papers.