On a bilingual NSPS benchmark, Korean language consistently lowers harmful compliance (~10pp TRS), Korean grounding often mitigates that drop, and open- vs closed-source models reverse under direct requests.
The tower of babel revisited: Multilin- gual jailbreak prompts on closed-source large language models.arXiv preprint arXiv:2505.12287,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
STEER is a gradient-guided attack that iteratively translates refusal-triggering words into low-resource languages to jailbreak LLMs, reaching 93-96.7% success on open models and 35.5% transfer to GPT-4o-mini.
citing papers explorer
-
ROK-FORTRESS: Measuring the Effect of Geopolitical Transcreation for National Security and Public Safety
On a bilingual NSPS benchmark, Korean language consistently lowers harmful compliance (~10pp TRS), Korean grounding often mitigates that drop, and open- vs closed-source models reverse under direct requests.
-
Safety Targeted Embedding Exploit via Refinement
STEER is a gradient-guided attack that iteratively translates refusal-triggering words into low-resource languages to jailbreak LLMs, reaching 93-96.7% success on open models and 35.5% transfer to GPT-4o-mini.