Safety Assessment of Chinese Large Language Models
A structured LLM safety taxonomy covering harmful content and adversarial attacks may inform how agencies frame AI risk assessments and procurement criteria.
Key points
- MIT AI Risk Repository spotlights a 2023 safety taxonomy for Chinese LLMs covering 8 harm scenarios and 6 adversarial attack types.
- The taxonomy claims scalability beyond Chinese-language models, making it potentially relevant to broader LLM safety evaluation work.
- This is a blog summary of a 2023 academic paper - useful reference material, not new guidance or policy.
Implications for Australian agencies
- Monitor Agencies developing AI risk assessment frameworks or procurement criteria may want to note this taxonomy as one of several available reference structures for categorising LLM safety risks.
- Consider Policy teams could assess whether the 8-scenario harm taxonomy and adversarial attack categories map usefully onto Australia's responsible AI guidance or agency-level risk registers.
Implications are AI-generated. Starting points, not advice — see methodology for how they're framed.
View original source
Copied.
Appeared in:
Weekly digest, 9 February 2026
"Safety Assessment of Chinese Large Language Models"
Source: MIT AI Risk Repository – Blog
Published: 9 February 2026
URL: https://airisk.mit.edu/blog/safety-assessment-of-chinese-large-language-models
The MIT AI Risk Repository's blog spotlights a 2023 paper by Sun et al. proposing a safety assessment framework for Chinese large language models. The framework comprises a taxonomy of 8 harmful content scenarios (including insult, discrimination, physical harm, and privacy exposure) and 6 adversarial instruction attack types (such as goal hijacking and role-play misuse), along with a benchmark and safety leaderboard assessing 15 LLMs. While developed for Chinese-language models, the authors note the taxonomy could scale to other languages and model families. The MIT blog entry is a summary rather than original research.
Implications for Australian agencies:
- [Monitor] Agencies developing AI risk assessment frameworks or procurement criteria may want to note this taxonomy as one of several available reference structures for categorising LLM safety risks.
- [Consider] Policy teams could assess whether the 8-scenario harm taxonomy and adversarial attack categories map usefully onto Australia's responsible AI guidance or agency-level risk registers.
Retrieved from SIMS, 18 July 2026.