# GPT-4 and Safety Case Generation: An Exploratory Analysis

arXiv: https://arxiv.org/abs/2312.05696 · HTML: https://mlsanity.com/paper/2312.05696/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 30 references that are in the map.
- First posted on arXiv 9 Dec 2023.

## Builds on (most cited first, 3 of 3)

- [Understanding the Behaviors of BERT in Ranking](https://mlsanity.com/paper/1904.07531/) (2019)
- [Towards using Few-Shot Prompt Learning for Automating Model Completion](https://mlsanity.com/paper/2212.03404/) (2022)
- [A Methodology for Automating Assurance Case Generation](https://mlsanity.com/paper/2003.05388/) (2020)

## Built on by (most cited first, 2 of 2)

- [CoDefeater: Using LLMs To Find Defeaters in Assurance Cases](https://mlsanity.com/paper/2407.13717/) (2024)
- [Evaluating Assurance Cases as Text-Attributed Graphs for Structure and Provenance Analysis](https://mlsanity.com/paper/2604.20577/) (2026)

## Abstract (arXiv)

In the ever-evolving landscape of software engineering, the emergence of large language models (LLMs) and conversational interfaces, exemplified by ChatGPT, is nothing short of revolutionary. While their potential is undeniable across various domains, this paper sets out on a captivating expedition to investigate their uncharted territory, the exploration of generating safety cases. In this paper, our primary objective is to delve into the existing knowledge base of GPT-4, focusing specifically on its understanding of the Goal Structuring Notation (GSN), a well-established notation allowing to visually represent safety cases. Subsequently, we perform four distinct experiments with GPT-4. These experiments are designed to assess its capacity for generating safety cases within a defined system and application domain. To measure the performance of GPT-4 in this context, we compare the results it generates with ground-truth safety cases created for an X-ray system system and a Machine-Learning (ML)-enabled component for tire noise recognition (TNR) in a vehicle. This allowed us to gain valuable insights into the model's generative capabilities. Our findings indicate that GPT-4 demonstrates the capacity to produce safety arguments that are moderately accurate and reasonable. Furthermore, it exhibits the capability to generate safety cases that closely align with the semantic content of the reference safety cases used as ground-truths in our experiments.