Don't Want Your LLM to Recommend Nuclear Strike? Try Asking It in Japanese

arXiv cs.AIAugust 15, 2026en

arXiv cs.AI

AI Global Wire

arXiv:2608.12373v1 Announce Type: new Abstract: Large language models are increasingly used in strategic and advisory contexts, yet their safety alignment is typically evaluated in English only. We test nine models from six providers and ask whether the language of a prompt can change a model's decision in a high-stakes scenario. We use single-turn game-theoretic vignettes in which a model advises a nuclear-armed nation on whether to strike a defenseless opponent. The prompt is intentionally amoral and strategically identical across languages. We find that Japanese prompts reduce launch rates in the Claude model family: Claude Sonnet 4.6 drops from 40% to 0% in scenarios where the strike is

This is a short summary published by AI Global Wire. The full article is owned and hosted by arXiv cs.AI — open it there to read it in full.

• Anthropic
• Forskning