7 papers
On the Impact of Code Comments for Automated Bug-Fixing: An Empirical Study
Antonio Vitale, Emanuela Guglielmi, Simone Scalabrino +1
Large Language Models (LLMs) are increasingly relevant in Software Engineering research and practice, with Automated Bug Fixing (ABF) being one of their key applications. ABF invol…
Toward Explaining Large Language Models in Software Engineering Tasks
Antonio Vitale, Khai-Nguyen Nguyen, Denys Poshyvanyk +3
Recent progress in Large Language Models (LLMs) has substantially advanced the automation of software engineering (SE) tasks, enabling complex activities such as code generation an…
Beyond Code Similarity: Benchmarking the Plausibility, Efficiency, and Complexity of LLM-Generated Smart Contracts
Francesco Salzano, Simone Scalabrino, Rocco Oliveto +1
Smart Contracts are critical components of blockchain ecosystems, with Solidity as the dominant programming language. While LLMs excel at general-purpose code generation, the uniqu…
How do Copilot Suggestions Impact Developers' Frustration and Productivity?
Emanuela Guglielmi, Venera Arnoudova, Gabriele Bavota +2
Context. AI-based development tools, such as GitHub Copilot, are transforming the software development process by offering real-time code suggestions. These tools promise to improv…
Identifying and Replicating Code Patterns Driving Performance Regressions in Software Systems
Denivan Campos, Luana Martins, Emanuela Guglielmi +6
Context: Performance regressions negatively impact execution time and memory usage of software systems. Nevertheless, there is a lack of systematic methods to evaluate the effectiv…
Personalized Code Readability Assessment: Are We There Yet?
Antonio Vitale, Emanuela Guglielmi, Rocco Oliveto +1
Unreadable code could be a breeding ground for errors. Thus, previous work defined approaches based on machine learning to automatically assess code readability that can warn devel…