Designing Empirical Studies on LLM-Based Code Generation: Towards a Reference Framework

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Nascimento, Nathalia, Guimaraes, Everton, Alencar, Paulo
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908577077133312
author Nascimento, Nathalia
Guimaraes, Everton
Alencar, Paulo
author_facet Nascimento, Nathalia
Guimaraes, Everton
Alencar, Paulo
contents The rise of large language models (LLMs) has introduced transformative potential in automated code generation, addressing a wide range of software engineering challenges. However, empirical evaluation of LLM-based code generation lacks standardization, with studies varying widely in goals, tasks, and metrics, which limits comparability and reproducibility. In this paper, we propose a theoretical framework for designing and reporting empirical studies on LLM-based code generation. The framework is grounded in both our prior experience conducting such experiments and a comparative analysis of key similarities and differences among recent studies. It organizes evaluation around core components such as problem sources, quality attributes, and metrics, supporting structured and systematic experimentation. We demonstrate its applicability through representative case mappings and identify opportunities for refinement. Looking forward, we plan to evolve the framework into a more robust and mature tool for standardizing LLM evaluation across software engineering contexts.
format Preprint
id arxiv_https___arxiv_org_abs_2510_03862
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Designing Empirical Studies on LLM-Based Code Generation: Towards a Reference Framework
Nascimento, Nathalia
Guimaraes, Everton
Alencar, Paulo
Software Engineering
Artificial Intelligence
500
The rise of large language models (LLMs) has introduced transformative potential in automated code generation, addressing a wide range of software engineering challenges. However, empirical evaluation of LLM-based code generation lacks standardization, with studies varying widely in goals, tasks, and metrics, which limits comparability and reproducibility. In this paper, we propose a theoretical framework for designing and reporting empirical studies on LLM-based code generation. The framework is grounded in both our prior experience conducting such experiments and a comparative analysis of key similarities and differences among recent studies. It organizes evaluation around core components such as problem sources, quality attributes, and metrics, supporting structured and systematic experimentation. We demonstrate its applicability through representative case mappings and identify opportunities for refinement. Looking forward, we plan to evolve the framework into a more robust and mature tool for standardizing LLM evaluation across software engineering contexts.
title Designing Empirical Studies on LLM-Based Code Generation: Towards a Reference Framework
topic Software Engineering
Artificial Intelligence
500
url https://arxiv.org/abs/2510.03862