Welcome Your New AI Teammate: On Safety Analysis by Leashing Large Language Models

被引：2

作者：

Nouri, Ali ^{[1
,2
]}

Cabrero-Daniel, Beatriz ^{[3
]}

Torner, Fredrik ^{[1
]}

Sivencrona, Hakan ^{[4
]}

Berger, Christian ^{[3
]}

机构：

[1] Volvo Cars, Gothenburg, Sweden

[2] Chalmers Univ Technol, Gothenburg, Sweden

[3] Univ Gothenburg, Dept Comp Sci, Gothenburg, Sweden

[4] Zenseact, Gothenburg, Sweden

来源：

PROCEEDINGS 2024 IEEE/ACM 3RD INTERNATIONAL CONFERENCE ON AI ENGINEERING-SOFTWARE ENGINEERING FOR AI, CAIN 2024 | 2024年

关键词：

Hazard Analysis Risk Assessment; Autonomous Vehicles; DevOps; Safety; Large Language Model; Prompt Engineering; LLM; ChatGPT;

D O I：

10.1145/3644815.3644953

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

DevOps is a necessity in many industries, including the development of Autonomous Vehicles. In those settings, there are iterative activities that reduce the speed of SafetyOps cycles. One of these activities is "Hazard Analysis & Risk Assessment" (HARA), which is an essential step to start the safety requirements specification. As a potential approach to increase the speed of this step in SafetyOps, we have delved into the capabilities of Large Language Models (LLMs). Our objective is to systematically assess their potential for application in the field of safety engineering. To that end, we propose a framework to support a higher degree of automation of HARA with LLMs. Despite our endeavors to automate as much of the process as possible, expert review remains crucial to ensure the validity and correctness of the analysis results, with necessary modifications made accordingly.

引用

页码：172 / 177

页数：6

共 17 条

[1]

[Anonymous], 2022, ISO 21448:2022

[2]

[Anonymous], 2018, ISO 26262:2018 (all parts)

[3]

[Anonymous], 2021, 5G Observatory Quarterly Report 13 Up to October 2021

[4]

Bommasani R., 2022, ARXIV, DOI DOI 10.48550/ARXIV.2108.07258

[5]

Diemert S., 2023, Can large language models assist in hazard analysis?

[6]

Gilson A., 2022, How well does chatgpt do when taking the medical licensing exams? the implications of large language models for medical education and knowledge assessment, V12

[7] Prompt Engineering with ChatGPT: A Guide for Academic Writers [J].