Redirecting to original paper in 30 seconds...
Click below to go immediately or wait for automatic redirect
📄 Abstract
Abstract: In this work, we propose LiveSecBench, a dynamic and continuously updated
safety benchmark specifically for Chinese-language LLM application scenarios.
LiveSecBench evaluates models across six critical dimensions (Legality, Ethics,
Factuality, Privacy, Adversarial Robustness, and Reasoning Safety) rooted in
the Chinese legal and social frameworks. This benchmark maintains relevance
through a dynamic update schedule that incorporates new threat vectors, such as
the planned inclusion of Text-to-Image Generation Safety and Agentic Safety in
the next update. For now, LiveSecBench (v251030) has evaluated 18 LLMs,
providing a landscape of AI safety in the context of Chinese language. The
leaderboard is publicly accessible at https://livesecbench.intokentech.cn/.
Key Contributions
This paper introduces LiveSecBench, a dynamic and continuously updated AI safety benchmark specifically tailored for Chinese-language LLM applications. It evaluates models across six critical dimensions (Legality, Ethics, Factuality, Privacy, Adversarial Robustness, Reasoning Safety) grounded in Chinese legal and social frameworks, ensuring relevance through dynamic updates and incorporating emerging threat vectors like text-to-image and agentic safety.
Business Value
Enables developers and deployers of LLMs in China to ensure compliance with local regulations and societal norms, reducing risks and building user trust.