arXiv Machine Learning
Is Refusal Direction Universal across Low-Resourced Languages?
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv AI
Sep 24
Hard Negatives Reveal What Easy Negatives Hide: Cross-Lingual Harmfulness Representations Degrade with Resource Tier Under Hard Negatives
The study investigates how safety alignment in large language models, trained mainly in English, transfers to other languages. While models show near-perfect harmfulness detection (AUROC > 0.98) using unrelated harmless prompts (easy negatives), performance drops sharply in low‑resource languages when using surface‑similar benign prompts (hard negatives). This degradation persists across multiple languages and models, indicating that easy‑negative evaluation alone cannot confirm cross‑lingual harmfulness representation quality.
arXiv AI
Jun 2
Low-Resource Safety Failures Are Action Failures, Not Representation Failures
arXiv:2606. 01196v1 Announce Type: cross Abstract: Safety alignment learned in high-resource languages transfers poorly to low-resource languages.
arXiv Computation and Language
Aug 24
Language Shapes Instruction Hierarchy Compliance in Multilingual LLMs
The paper introduces XIH-Bench, a multilingual benchmark for evaluating instruction hierarchy (IH) compliance in large language models across six languages, four domains, and three IH settings. It finds that IH compliance varies with language, showing an asymmetry where a language can strengthen compliance in a higher-priority role but disrupt it in a lower-priority role, and that cross-language conflicts yield higher compliance than same-language conflicts—a phenomenon called the Language Boundary Effect. The study also highlights that language specialization can make lower-priority instructions in favored languages harder to override, raising potential reliability and security concerns.
arXiv AI
Jul 14
Minionese: Comprehensive Benchmark and Mechanistic Study of Multilingual LLM Safety
arXiv:2607. 10112v1 Announce Type: cross Abstract: 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.
Hugging Face Trending Papers
Aug 11
The Illusion of Cross-Lingual Safety in Low-Resource Languages
Safety alignment in large language models (LLMs) is largely developed in English, assuming these safeguards generalize across multilingual settings. However, this assumption remains underexplored and exposes a vulnerability in low-resource languages.
arXiv AI
3d ago
Global Security Blind Spots: Translation as a Safety Bypass in Low-Resource Languages
The paper investigates how large language models (LLMs) can be bypassed by translating harmful requests from English into low‑resource languages. By testing ten popular LLMs across 79 languages, the authors find that safe English completions often fail to remain safe after translation, with bypass rates between 21.9% and 44.4%. The risk is unevenly distributed across language families and varies significantly between models, making it hard to rank models by safety consistently.