Safety Analysis in the Era of Large Language Models: A Case Study of STPA using ChatGPT
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2023
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917920361152512 |
|---|---|
| author | Qi, Yi Zhao, Xingyu Khastgir, Siddartha Huang, Xiaowei |
| author_facet | Qi, Yi Zhao, Xingyu Khastgir, Siddartha Huang, Xiaowei |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2304_01246 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Safety Analysis in the Era of Large Language Models: A Case Study of STPA using ChatGPT Qi, Yi Zhao, Xingyu Khastgir, Siddartha Huang, Xiaowei Computation and Language Artificial Intelligence Computers and Society Software Engineering 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. |
| title | Safety Analysis in the Era of Large Language Models: A Case Study of STPA using ChatGPT |
| topic | Computation and Language Artificial Intelligence Computers and Society Software Engineering |
| url | https://arxiv.org/abs/2304.01246 |