Investigating the Use of LLMs for Evidence Briefings Generation in Software Engineering

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Marcelino, Mauro, Alves, Marcos, Trinkenreich, Bianca, Cartaxo, Bruno, Soares, Sérgio, Barbosa, Simone D. J., Kalinowski, Marcos
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911068063793152
author Marcelino, Mauro
Alves, Marcos
Trinkenreich, Bianca
Cartaxo, Bruno
Soares, Sérgio
Barbosa, Simone D. J.
Kalinowski, Marcos
author_facet Marcelino, Mauro
Alves, Marcos
Trinkenreich, Bianca
Cartaxo, Bruno
Soares, Sérgio
Barbosa, Simone D. J.
Kalinowski, Marcos
contents [Context] An evidence briefing is a concise and objective transfer medium that can present the main findings of a study to software engineers in the industry. Although practitioners and researchers have deemed Evidence Briefings useful, their production requires manual labor, which may be a significant challenge to their broad adoption. [Goal] The goal of this registered report is to describe an experimental protocol for evaluating LLM-generated evidence briefings for secondary studies in terms of content fidelity, ease of understanding, and usefulness, as perceived by researchers and practitioners, compared to human-made briefings. [Method] We developed an RAG-based LLM tool to generate evidence briefings. We used the tool to automatically generate two evidence briefings that had been manually generated in previous research efforts. We designed a controlled experiment to evaluate how the LLM-generated briefings compare to the human-made ones regarding perceived content fidelity, ease of understanding, and usefulness. [Results] To be reported after the experimental trials. [Conclusion] Depending on the experiment results.
format Preprint
id arxiv_https___arxiv_org_abs_2507_15828
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Investigating the Use of LLMs for Evidence Briefings Generation in Software Engineering
Marcelino, Mauro
Alves, Marcos
Trinkenreich, Bianca
Cartaxo, Bruno
Soares, Sérgio
Barbosa, Simone D. J.
Kalinowski, Marcos
Software Engineering
[Context] An evidence briefing is a concise and objective transfer medium that can present the main findings of a study to software engineers in the industry. Although practitioners and researchers have deemed Evidence Briefings useful, their production requires manual labor, which may be a significant challenge to their broad adoption. [Goal] The goal of this registered report is to describe an experimental protocol for evaluating LLM-generated evidence briefings for secondary studies in terms of content fidelity, ease of understanding, and usefulness, as perceived by researchers and practitioners, compared to human-made briefings. [Method] We developed an RAG-based LLM tool to generate evidence briefings. We used the tool to automatically generate two evidence briefings that had been manually generated in previous research efforts. We designed a controlled experiment to evaluate how the LLM-generated briefings compare to the human-made ones regarding perceived content fidelity, ease of understanding, and usefulness. [Results] To be reported after the experimental trials. [Conclusion] Depending on the experiment results.
title Investigating the Use of LLMs for Evidence Briefings Generation in Software Engineering
topic Software Engineering
url https://arxiv.org/abs/2507.15828