Evaluating the Capability of LLMs in Identifying Compilation Errors in Configurable Systems

TL;DR

This paper assesses the effectiveness of large language models like ChatGPT4 in detecting compilation errors in configurable systems, demonstrating their potential to assist developers despite some limitations.

Contribution

It is the first comprehensive evaluation of LLMs for identifying compilation errors in configurable systems across multiple languages and error types.

Findings

ChatGPT4 successfully identified most errors in various systems.

Le Chat Mistral and Gemini detected some errors, but less comprehensively.

LLMs show promise as tools for error detection in complex configurable systems.

Abstract

Compilation is an important process in developing configurable systems, such as Linux. However, identifying compilation errors in configurable systems is not straightforward because traditional compilers are not variability-aware. Previous approaches that detect some of these compilation errors often rely on advanced techniques that require significant effort from programmers. This study evaluates the efficacy of Large Language Models (LLMs), specifically ChatGPT4, Le Chat Mistral and Gemini Advanced 1.5, in identifying compilation errors in configurable systems. Initially, we evaluate 50 small products in C++, Java, and C languages, followed by 30 small configurable systems in C, covering 17 different types of compilation errors. ChatGPT4 successfully identified most compilation errors in individual products and in configurable systems, while Le Chat Mistral and Gemini Advanced 1.5 detected some of them. LLMs have shown potential in assisting developers in identifying compilation errors in configurable systems.