Software testing with large language models: Survey, landscape, and vision
Pre-trained large language models (LLMs) have recently emerged as a breakthrough
technology in natural language processing and artificial intelligence, with the ability to …
technology in natural language processing and artificial intelligence, with the ability to …
Code generation using machine learning: A systematic review
Recently, machine learning (ML) methods have been used to create powerful language
models for a broad range of natural language processing tasks. An important subset of this …
models for a broad range of natural language processing tasks. An important subset of this …
Automated program repair in the era of large pre-trained language models
Automated Program Repair (APR) aims to help developers automatically patch software
bugs. However, current state-of-the-art traditional and learning-based APR techniques face …
bugs. However, current state-of-the-art traditional and learning-based APR techniques face …
Codamosa: Escaping coverage plateaus in test generation with pre-trained large language models
Search-based software testing (SBST) generates high-coverage test cases for programs
under test with a combination of test case generation and mutation. SBST's performance …
under test with a combination of test case generation and mutation. SBST's performance …
An empirical evaluation of using large language models for automated unit test generation
Unit tests play a key role in ensuring the correctness of software. However, manually
creating unit tests is a laborious task, motivating the need for automation. Large Language …
creating unit tests is a laborious task, motivating the need for automation. Large Language …
Retrieval-based prompt selection for code-related few-shot learning
Large language models trained on massive code corpora can generalize to new tasks
without the need for task-specific fine-tuning. In few-shot learning, these models take as …
without the need for task-specific fine-tuning. In few-shot learning, these models take as …
No more manual tests? evaluating and improving chatgpt for unit test generation
Unit testing is essential in detecting bugs in functionally-discrete program units. Manually
writing high-quality unit tests is time-consuming and laborious. Although traditional …
writing high-quality unit tests is time-consuming and laborious. Although traditional …
Studying the usage of text-to-text transfer transformer to support code-related tasks
Deep learning (DL) techniques are gaining more and more attention in the software
engineering community. They have been used to support several code-related tasks, such …
engineering community. They have been used to support several code-related tasks, such …
On the robustness of code generation techniques: An empirical study on github copilot
A Mastropaolo, L Pascarella… - 2023 IEEE/ACM 45th …, 2023 - ieeexplore.ieee.org
Software engineering research has always being concerned with the improvement of code
completion approaches, which suggest the next tokens a developer will likely type while …
completion approaches, which suggest the next tokens a developer will likely type while …
Using pre-trained models to boost code review automation
Code review is a practice widely adopted in open source and industrial projects. Given the
non-negligible cost of such a process, researchers started investigating the possibility of …
non-negligible cost of such a process, researchers started investigating the possibility of …