Don't Want Your LLM to Recommend Nuclear Strike? Try Asking It in Japanese
A new study shows LLM safety behavior changes with prompt language: Japanese prompts sharply reduce nuclear strike recommendations in Claude and Gemini models, even though the strategic content is identical. The effect is driven by the language the model is asked to reason in, not the input language.
-->
[Submitted on 21 Jul 2026]
Title:Don't Want Your LLM to Recommend Nuclear Strike? Try Asking It in Japanese
View a PDF of the paper titled Don't Want Your LLM to Recommend Nuclear Strike? Try Asking It in Japanese, by Rian Touchent (ALMAnaCH)
View PDF
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 unnecessary and from 93% to 17% in contested scenarios, with minimal effect when the strike is strategically rational. The effect extends to Gemini Pro 3.1 (53% to 13%). A cross-language experiment isolates the mechanism: when instructed to reason in Japanese in an English prompt, launch rates drop from 93% to 37%. It is the language the model is asked to reason in, not the language of the input, that drives the effect. When reasoning in Japanese, models spontaneously generate moral vocabulary (''moral cost'', ''millions of lives'') that is entirely absent from the prompt. Five other models show no language effect, but they launch in nearly every condition regardless of language. The effect requires a model that already hesitates in English. These results show that LLM safety behavior is language-dependent, and that evaluating in English alone can miss both risks and safeguards encoded in other languages.
Subjects:
Artificial Intelligence (cs.AI)
Cite as: arXiv:2608.12373 [cs.AI]
(or arXiv:2608.12373v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2608.12373
arXiv-issued DOI via DataCite
Journal reference: Proceedings of the 6th Workshop on Trustworthy NLP (TrustNLP 2026), Jul 2026, San Diego, United States. pp.489-502
Submission history
From: Rian Touchent [view email] [via CCSD proxy] [v1] Tue, 21 Jul 2026 10:09:45 UTC (68 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Don't Want Your LLM to Recommend Nuclear Strike? Try Asking It in Japanese, by Rian Touchent (ALMAnaCH)
View PDF
TeX Source
view license
Current browse context:
cs.AI
new | recent | 2026-08
Change to browse by:
cs
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
Loading...
Data provided by:
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)