GPT-Based Models Meet Simulation: How to Efficiently Use Large-Scale Pre-Trained Language Models Across Simulation Tasks

TL;DR

This paper explores the novel application of large-scale pre-trained language models like GPT-4 in scientific simulations, assessing their benefits and limitations across four key tasks to guide effective usage.

Contribution

It is the first study to systematically evaluate LLMs for scientific simulation tasks and provides practical guidance for modelers on their application.

Findings

LLMs can explain conceptual models effectively.

LLMs assist in summarizing simulation outputs.

LLMs help convey visualization insights via text.

Abstract

The disruptive technology provided by large-scale pre-trained language models (LLMs) such as ChatGPT or GPT-4 has received significant attention in several application domains, often with an emphasis on high-level opportunities and concerns. This paper is the first examination regarding the use of LLMs for scientific simulations. We focus on four modeling and simulation tasks, each time assessing the expected benefits and limitations of LLMs while providing practical guidance for modelers regarding the steps involved. The first task is devoted to explaining the structure of a conceptual model to promote the engagement of participants in the modeling process. The second task focuses on summarizing simulation outputs, so that model users can identify a preferred scenario. The third task seeks to broaden accessibility to simulation platforms by conveying the insights of simulation visualizations via text. Finally, the last task evokes the possibility of explaining simulation errors and providing guidance to resolve them.