Safety Analysis in the Era of Large Language Models: A Case Study of STPA using ChatGPT
This addresses safety analysis challenges for engineers and regulators in high-stakes domains, but it is incremental as it builds on existing STPA methods with LLMs.
The study tackled the problem of whether Large Language Models (LLMs) can be used for safety analysis by applying ChatGPT to Systems Theoretic Process Analysis (STPA) on Automatic Emergency Brake and Electricity Demand Side Management systems, finding that with careful design, it may outperform human experts but reliability issues persist without intervention.
Can safety analysis make use of Large Language Models (LLMs)? A case study explores Systems Theoretic Process Analysis (STPA) applied to Automatic Emergency Brake (AEB) and Electricity Demand Side Management (DSM) systems using ChatGPT. We investigate how collaboration schemes, input semantic complexity, and prompt guidelines influence STPA results. Comparative results show that using ChatGPT without human intervention may be inadequate due to reliability related issues, but with careful design, it may outperform human experts. No statistically significant differences are found when varying the input semantic complexity or using common prompt guidelines, which suggests the necessity for developing domain-specific prompt engineering. We also highlight future challenges, including concerns about LLM trustworthiness and the necessity for standardisation and regulation in this domain.