From the 1 of 5 linked papers with an AI index.
5 papers
SemaDiff: Identifying Semantic-Changing Commits with Generated Code and Tests
Maha Ayub, Michael Konstantinou, Ahmed Khanfir +2
The paper introduces SemaDiff, a method that uses large language models to generate additional calling code and tests in order to compare the behavior of pre- and post‑commit versi…
On the risk of coding before testing: An empirical study on LLM-based test generation workflow
Michael Konstantinou, Florian Tambon, Mike Papadakis
Large Language Models (LLMs) are increasingly used in software engineering workflows to generate both source code and test suites. This dual capability has enabled emerging develop…
Prompt Coverage Adequacy
Florian Tambon, Michael Konstantinou, Cedric Richter +3
In recent years, it has become increasingly evident that large language models (LLMs) and autonomous agents raise the level of abstraction in software development by shifting the f…
How well LLM-based test generation techniques perform with newer LLM versions?
Michael Konstantinou, Renzo Degiovanni, Mike Papadakis
The rapid evolution of Large Language Models (LLMs) has strongly impacted software engineering, leading to a growing number of studies on automated unit test generation. However, t…
YATE: The Role of Test Repair in LLM-Based Unit Test Generation
Michael Konstantinou, Renzo Degiovanni, Jie M. Zhang +2
Recent advances in automated test generation utilises language models to produce unit tests. While effective, language models tend to generate many incorrect tests with respect to…