Large language models for software engineering: Survey and open problems

A Fan, B Gokkaya, M Harman… - 2023 IEEE/ACM …, 2023 - ieeexplore.ieee.org
This paper provides a survey of the emerging area of Large Language Models (LLMs) for
Software Engineering (SE). It also sets out open research challenges for the application of …

Measuring GitHub Copilot's Impact on Productivity

A Ziegler, E Kalliamvakou, XA Li, A Rice… - Communications of the …, 2024 - dl.acm.org
Measuring GitHub Copilot's Impact on Productivity Page 1 CODE-COMPLETION SYSTEMS
OFFERING suggestions to a developer in their integrated development environment (IDE) …

In-IDE Human-AI Experience in the Era of Large Language Models; A Literature Review

A Sergeyuk, S Titov, M Izadi - Proceedings of the 1st ACM/IEEE …, 2024 - dl.acm.org
Integrated Development Environments (IDEs) have become central to modern software
development, especially with the integration of Artificial Intelligence (AI) to enhance …

[HTML][HTML] DCServCG: A data-centric service code generation using deep learning

Z Alizadehsani, H Ghaemi, A Shahraki… - … Applications of Artificial …, 2023 - Elsevier
Modern software development paradigms, including Service-Oriented Architecture (SOA),
tend to make use of available services eg, web service Application Programming Interfaces …

xastnn: Improved code representations for industrial practice

Z Xu, M Zhou, X Zhao, Y Chen, X Cheng… - Proceedings of the 31st …, 2023 - dl.acm.org
The application of deep learning techniques in software engineering becomes increasingly
popular. One key problem is developing high-quality and easy-to-use source code …

Completing Function Documentation Comments Using Structural Information

A Ciurumelea, CV Alexandru, HC Gall… - Empirical Software …, 2023 - Springer
Source code comments are a cornerstone of software documentation facilitating feature
development and maintenance. Well-defined documentation formats, like Javadoc, make it …

Learning Transfers over Several Programming Languages

R Baltaji, S Pujar, L Mandel, M Hirzel, L Buratti… - arXiv preprint arXiv …, 2023 - arxiv.org
Large language models (LLMs) have recently become remarkably good at improving
developer productivity for high-resource programming languages. These models use two …

RLCoder: Reinforcement Learning for Repository-Level Code Completion

Y Wang, Y Wang, D Guo, J Chen, R Zhang… - arXiv preprint arXiv …, 2024 - arxiv.org
Repository-level code completion aims to generate code for unfinished code snippets within
the context of a specified repository. Existing approaches mainly rely on retrieval-augmented …

Milo: Attacking Deep Pre-trained Model for Programming Languages Tasks with Anti-analysis Code Obfuscation

L Song, SHH Ding - 2023 IEEE 47th Annual Computers …, 2023 - ieeexplore.ieee.org
Deep neural networks, especially pre-trained BERT models, have been widely applied in
programming language processing tasks and achieved promising results. Their down …

Machine learning for executable code in software testing and verification

P Nie - 2023 - repositories.lib.utexas.edu
Software testing and verification are essential for keeping software systems reliable and safe
to use. However, it requires significant manual effort to write and maintain code artifacts …