Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systems

4 Sep 2024 · MIT AI Risk Repository – Blog Global

A structured LLM risk taxonomy with mitigation strategies offers a ready-made reference for APS teams developing AI risk assessment or procurement criteria.

Key points

Summary

This MIT AI Risk Repository blog post summarises an academic framework by Cui and colleagues (2024) that categorises LLM risks across four system modules: input, language model, toolchain, and output. The taxonomy identifies 12 specific risks and 44 sub-topics - including prompt injection, hallucinations, privacy leakage, and hardware vulnerabilities - and pairs each module with mitigation strategies and assessment benchmarks. While not a government standard, the module-oriented structure is practically useful for agencies conducting AI risk assessments, developing procurement requirements, or reviewing vendor claims about LLM safety.

Implications for Australian agencies

Implications are AI-generated. Starting points, not advice.