How can large language models assist with a FRAM analysis? (January 2025)

Summary

Large Language Models (LLMs) are transforming the way in which people interact with artificial intelligence. This study explores how safety professionals might use LLMs for a FRAM analysis.

The authors use interactive prompting with Google Bard / Gemini and ChatGPT to do a FRAM analysis on examples from healthcare and aviation.

The exploratory findings suggest that LLMs afford safety analysts the opportunity to enhance the FRAM analysis by facilitating initial model generation and offering different perspectives. Responsible and effective utilisation of LLMs requires careful consideration of their limitations as well as their abilities. Human expertise is crucial both with regards to validating the output of the LLM as well as in developing meaningful interactive prompting strategies to take advantage of LLM capabilities such as self-critiquing from different perspectives.

Further research is required on effective prompting strategies, and to address ethical concerns.