Minionese: Comprehensive Benchmark and Mechanistic Study of Multilingual LLM Safety
Safety alignment in large language models remains brittle across languages: prompts reliably refused in English can elicit harmful compliance in non-English and low-resource settings. We introduce \textsc{Minionese}, a multilingual jailbreak benchmark spanning 18 languages, 4 resource tiers, and 4 perturbation types (standard translation, code-switching, transliteration, and translationese), paired with a geometric mechanistic analysis of refusal failure across language tiers. We show that each
Record details
Published: 11 July 2026
Source: arXiv
Category: Research
Topics: Regulation · Safety & alignment
Retrieved: 14 July 2026
Related evidence
These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.
Geopolitical alignment: Endorsement effects in large language models
arXiv · 10 July 2026
WasteAssistant: Regulation-Guided Visual Question Answering Framework for Intelligent Waste Segregation and Sustainable Managemen
arXiv · 12 July 2026
Proxy Exploration and Reusable Guidance: A Modular LLM Post-Training Paradigm via Proxy-Guided Update Signals
HuggingFace Daily Papers · 13 July 2026
HyperSafe: Inference-Time Safety Recovery for Fine-Tuned Language Models
arXiv cs.LG · 13 July 2026
Proxy Exploration and Reusable Guidance: A Modular LLM Post-Training Paradigm via Proxy-Guided Update Signals
arXiv · 13 July 2026
Operationalising Multi-Dimensional Evaluation for Conversational Agents: A Scalable, Governed Pipeline with Selective Re-evaluation and Model Benchmarking
arXiv · 13 July 2026
How to cite this record
ethics.ai (11 July 2026), “Minionese: Comprehensive Benchmark and Mechanistic Study of Multilingual LLM Safety,” evidence record 54, https://ethics.ai/record/54 (originally published by arXiv).
Use and limitations
This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.