Competition-level code generation with alphacode
Programming is a powerful and ubiquitous problem-solving tool. Systems that can assist
programmers or even generate programs themselves could make programming more …
programmers or even generate programs themselves could make programming more …
Productivity assessment of neural code completion
A Ziegler, E Kalliamvakou, XA Li, A Rice… - Proceedings of the 6th …, 2022 - dl.acm.org
Neural code synthesis has reached a point where snippet generation is accurate enough to
be considered for integration into human software development workflows. Commercial …
be considered for integration into human software development workflows. Commercial …
Codefill: Multi-token code completion by jointly learning from structure and naming sequences
Code completion is an essential feature of IDEs, yet current auto-completers are restricted to
either grammar-based or NLP-based single token completions. Both approaches have …
either grammar-based or NLP-based single token completions. Both approaches have …
Code prediction by feeding trees to transformers
Code prediction, more specifically autocomplete, has become an essential feature in
modern IDEs. Autocomplete is more effective when the desired next token is at (or close to) …
modern IDEs. Autocomplete is more effective when the desired next token is at (or close to) …
Exploring the potential of chatgpt in automated code refinement: An empirical study
Code review is an essential activity for ensuring the quality and maintainability of software
projects. However, it is a time-consuming and often error-prone task that can significantly …
projects. However, it is a time-consuming and often error-prone task that can significantly …
An empirical study on the usage of transformer models for code completion
Code completion aims at speeding up code writing by predicting the next code token (s) the
developer is likely to write. Works in this field focused on improving the accuracy of the …
developer is likely to write. Works in this field focused on improving the accuracy of the …
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) …
OFFERING suggestions to a developer in their integrated development environment (IDE) …
Counterfactual explanations for models of code
Machine learning (ML) models play an increasingly prevalent role in many software
engineering tasks. However, because most models are now powered by opaque deep …
engineering tasks. However, because most models are now powered by opaque deep …
Fast and memory-efficient neural code completion
Code completion is one of the most widely used features of modern integrated development
environments (IDEs). While deep learning has made significant progress in the statistical …
environments (IDEs). While deep learning has made significant progress in the statistical …
Think outside the code: Brainstorming boosts large language models in code generation
XY Li, JT Xue, Z Xie, M Li - arXiv preprint arXiv:2305.10679, 2023 - arxiv.org
Code generation aims to automatically generate source code from high-level task
specifications, which can significantly increase productivity of software engineering …
specifications, which can significantly increase productivity of software engineering …