4 papers · 1 filter
Large Language Models for Code Generation from Multilingual Prompts: A Curated Benchmark and a Study on Code Quality
Saima Afrin, Alessandro Midolo, Camilo Escobar-Velásquez +5
Large Language Models (LLMs) perform differently on identical programming tasks when prompted in different natural languages, a phenomenon known as language bias. While this behavi…
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…
Automated Refactoring of Non-Idiomatic Python Code: A Differentiated Replication with LLMs
Alessandro Midolo, Massimiliano Di Penta
In the Python ecosystem, the adoption of idiomatic constructs has been fostered because of their expressiveness, increasing productivity and even efficiency, despite controversial…