Introduces a new dataset of 5,717 Kazakh safety evaluation prompts in 11 categories with baseline refusal rates showing English-only gaps.
arXiv preprint arXiv:2403.18314 , year =
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CL 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
CITA generates Chinese implicit toxicity samples that cause 69.48% average missed detection across seven tested detectors while preserving harmfulness, and the same data improves robustness when used to fine-tune a CITD defense model.
citing papers explorer
-
KZ-SafetyPrompts: A Kazakh Safety Evaluation Prompt Dataset for Large Language Models
Introduces a new dataset of 5,717 Kazakh safety evaluation prompts in 11 categories with baseline refusal rates showing English-only gaps.
-
Harder to Defend: Towards Chinese Toxicity Attacks via Implicit Enhancement and Obfuscation Rewriting
CITA generates Chinese implicit toxicity samples that cause 69.48% average missed detection across seven tested detectors while preserving harmfulness, and the same data improves robustness when used to fine-tune a CITD defense model.