Software Model Evolution with Large Language Models: Experiments on Simulated, Public, and Industrial Datasets

TL;DR

This paper investigates the use of large language models for software model evolution, proposing RAMC and demonstrating promising results across industrial, public, and simulated datasets.

Contribution

It introduces RAMC, a novel approach leveraging large language models and retrieval-augmented generation for software model completion, validated on diverse datasets.

Findings

62.30% semantically correct completions on industrial data

up to 86.19% type-correct completions

large language models excel with scarce or noisy data

Abstract

Modeling structure and behavior of software systems plays a crucial role in the industrial practice of software engineering. As with other software engineering artifacts, software models are subject to evolution. Supporting modelers in evolving software models with recommendations for model completions is still an open problem, though. In this paper, we explore the potential of large language models for this task. In particular, we propose an approach, RAMC, leveraging large language models, model histories, and retrieval-augmented generation for model completion. Through experiments on three datasets, including an industrial application, one public open-source community dataset, and one controlled collection of simulated model repositories, we evaluate the potential of large language models for model completion with RAMC. We found that large language models are indeed a promising technology for supporting software model evolution (62.30% semantically correct completions on real-world industrial data and up to 86.19% type-correct completions). The general inference capabilities of large language models are particularly useful when dealing with concepts for which there are few, noisy, or no examples at all.