大语言模型时代的安全分析:基于ChatGPT的STPA案例研究
Safety Analysis in the Era of Large Language Models: A Case Study of STPA using ChatGPT
AI总结:
本研究通过将ChatGPT应用于AEB和DSM系统的STPA安全分析案例,探究协作方案等因素对结果的影响,发现经精心设计的ChatGPT性能可超人类专家,且需开发领域特定提示工程。
摘要:
安全分析能否利用大语言模型(LLMs)?本案例研究探索将系统理论过程分析(STPA)应用于自动紧急制动(AEB)和电力需求侧管理(DSM)系统时使用ChatGPT的情况。我们调查协作方案、输入语义复杂度和提示指南如何影响STPA结果。对比结果显示,因可靠性相关问题,无人类干预使用ChatGPT可能不足,但经精心设计,其性能或优于人类专家。改变输入语义复杂度或使用通用提示指南时未发现统计学显著差异,这表明需开发领域特定的提示工程。我们还强调未来挑战,包括LLM可信度问题及该领域标准化与监管的必要性。
英文摘要:
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.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。