Empirical Evaluation of Large Language Models for Automated Unit Test Generation
Organisatsiooni nimi
Software Engineering Analytics
Kokkuvõte
Developers write unit tests to ensure software correctness, but manually writing these tests is time-consuming and could benefit from automation. Recently, Large Language Models (LLMs) have been applied to various aspects of software development, including the automated generation of unit tests. This thesis aims to empirically evaluate the effectiveness of LLMs in generating unit tests by comparing their performance against that of human testers.
Lõputöö kaitsmise aasta
2024-2025
Juhendaja
Faiz Ali Shah
Suhtlemiskeel(ed)
inglise keel
Nõuded kandideerijale
Tase
Magister
Märksõnad
Kandideerimise kontakt
Nimi
Faiz Ali Shah
Tel
E-mail