Beyond English and Evasion: A Human-Annotated Multi-Domain Benchmark for High-Stakes LLM Safety Evaluation in Chinese 事件

Beyond English and Evasion: A Human-Annotated Multi-Domain Benchmark for High-Stakes LLM Safety Evaluation in Chinese arXiv:2605.29667v1 Announce Type: new Abstract: When Large Language Models (LLMs) are deployed in Chinese-language settings, a troubling pattern emerges: safety systems that work well in English break down. These systems struggle to cross linguistic and cultural bound-aries, leaving models exposed to adversarial prompts that exploit Chinese-specific evasion techniques, including