Technique to Baseline QE Artefact Generation Aligned to Quality Metrics

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Farchi, Eitan, Nayak, Kiran, Majumdar, Papia Ghosh, Route, Saritha
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914164772962304
author Farchi, Eitan
Nayak, Kiran
Majumdar, Papia Ghosh
Route, Saritha
author_facet Farchi, Eitan
Nayak, Kiran
Majumdar, Papia Ghosh
Route, Saritha
contents Large Language Models (LLMs) are transforming Quality Engineering (QE) by automating the generation of artefacts such as requirements, test cases, and Behavior Driven Development (BDD) scenarios. However, ensuring the quality of these outputs remains a challenge. This paper presents a systematic technique to baseline and evaluate QE artefacts using quantifiable metrics. The approach combines LLM-driven generation, reverse generation , and iterative refinement guided by rubrics technique for clarity, completeness, consistency, and testability. Experimental results across 12 projects show that reverse-generated artefacts can outperform low-quality inputs and maintain high standards when inputs are strong. The framework enables scalable, reliable QE artefact validation, bridging automation with accountability.
format Preprint
id arxiv_https___arxiv_org_abs_2511_15733
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Technique to Baseline QE Artefact Generation Aligned to Quality Metrics
Farchi, Eitan
Nayak, Kiran
Majumdar, Papia Ghosh
Route, Saritha
Software Engineering
Artificial Intelligence
Large Language Models (LLMs) are transforming Quality Engineering (QE) by automating the generation of artefacts such as requirements, test cases, and Behavior Driven Development (BDD) scenarios. However, ensuring the quality of these outputs remains a challenge. This paper presents a systematic technique to baseline and evaluate QE artefacts using quantifiable metrics. The approach combines LLM-driven generation, reverse generation , and iterative refinement guided by rubrics technique for clarity, completeness, consistency, and testability. Experimental results across 12 projects show that reverse-generated artefacts can outperform low-quality inputs and maintain high standards when inputs are strong. The framework enables scalable, reliable QE artefact validation, bridging automation with accountability.
title Technique to Baseline QE Artefact Generation Aligned to Quality Metrics
topic Software Engineering
Artificial Intelligence
url https://arxiv.org/abs/2511.15733