7 papers
Machine Learning in the Wild: Early Evidence of Non-Compliant ML-Automation in Open-Source Software
Zohaib Arshid, Daniele Bifolco, Fiorella Zampetti +1
The increasing availability of Machine Learning (ML) models, particularly foundation models, enables their use across a range of downstream applications, from scenarios with missin…
Developers and Generative AI: A Study of Self-Admitted Usage in Open Source Projects
Rosalia Tufano, Federica Pepe, Fiorella Zampetti +4
The availability of generative Artificial Intelligence (AI) tools such as ChatGPT or GitHub Copilot is reshaping the way in which software is developed, evolved, and maintained. Of…
Evaluating the Impact of Post-Training Quantization on Large Language Models for Code Generation
Alessandro Giagnorio, Antonio Mastropaolo, Saima Afrin +2
Large Language Models (LLMs) have shown an impressive capability in code generation. The LLM effectiveness generally increases with its size: The higher the number of LLM's trainab…
How are MLOps Frameworks Used in Open Source Projects? An Empirical Characterization
Fiorella Zampetti, Federico Stocchetti, Federica Razzano +2
Machine Learning (ML) Operations (MLOps) frameworks have been conceived to support developers and AI engineers in managing the lifecycle of their ML models. While such frameworks p…
From Human to Machine Refactoring: Assessing GPT-4's Impact on Python Class Quality and Readability
Alessandro Midolo, Emiliano Tramontana, Massimiliano Di Penta
Refactoring is a software engineering practice that aims to improve code quality without altering program behavior. Although automated refactoring tools have been extensively studi…
Guidelines to Prompt Large Language Models for Code Generation: An Empirical Characterization
Alessandro Midolo, Alessandro Giagnorio, Fiorella Zampetti +3
Large Language Models (LLMs) are nowadays extensively used for various types of software engineering tasks, primarily code generation. Previous research has shown how suitable prom…