Generative AI in Evidence-Based Software Engineering: A White Paper
Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 reserved pith:FVNJOAF5record.jsonopen to challenge →
read the original 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
This paper has not been read by Pith yet.
Forward citations
Cited by 1 Pith paper
-
Beyond Accuracy: LLM Variability in Evidence Screening for Software Engineering SLRs
LLMs exhibit substantial heterogeneity and non-determinism in SLR evidence screening, abstracts are decisive for performance, and they show no reliable superiority over classical classifiers on two real SLRs.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.