Generative AI in Evidence-Based Software Engineering: A White Paper

TL;DR

This paper explores the rapid adoption of Generative AI in Evidence-Based Software Engineering, highlighting its potential to streamline literature reviews and analysis tasks, and proposes future empirical validation of AI models to support researchers.

Contribution

It provides a comprehensive overview of how Generative AI can transform evidence-based software engineering and outlines future plans for empirical validation of AI models.

Findings

Generative AI enables faster literature reviews.

AI models can assist in evidence synthesis.

Future validation will assess AI effectiveness in EBSE.

Abstract

Context. In less than a year practitioners and researchers witnessed a rapid and wide implementation of Generative Artificial Intelligence. The daily availability of new models proposed by practitioners and researchers has enabled quick adoption. Textual GAIs capabilities enable researchers worldwide to explore new generative scenarios simplifying and hastening all timeconsuming text generation and analysis tasks. Motivation. The exponentially growing number of publications in our field with the increased accessibility to information due to digital libraries makes conducting systematic literature reviews and mapping studies an effort and timeinsensitive task Stemmed from this challenge we investigated and envisioned the role of GAIs in evidencebased software engineering. Future Directions. Based on our current investigation we will follow up the vision with the creation and empirical validation of a comprehensive suite of models to effectively support EBSE researchers