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

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Albuquerque, Lucas, Gheyi, Rohit, Ribeiro, Márcio
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914892619972608
author Albuquerque, Lucas
Gheyi, Rohit
Ribeiro, Márcio
author_facet Albuquerque, Lucas
Gheyi, Rohit
Ribeiro, Márcio
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2407_19087
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Evaluating the Capability of LLMs in Identifying Compilation Errors in Configurable Systems
Albuquerque, Lucas
Gheyi, Rohit
Ribeiro, Márcio
Software Engineering
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.
title Evaluating the Capability of LLMs in Identifying Compilation Errors in Configurable Systems
topic Software Engineering
url https://arxiv.org/abs/2407.19087