Assessing the Security of GitHub Copilot's Generated Code-A Targeted Replication Study
V Majdinasab, MJ Bishop, S Rasheed… - … on Software Analysis …, 2024 - ieeexplore.ieee.org
AI-powered code generation models have been developing rapidly, allowing developers to
expedite code generation and thus improve their productivity. These models are trained on …
expedite code generation and thus improve their productivity. These models are trained on …
Sok: Memorization in general-purpose large language models
Large Language Models (LLMs) are advancing at a remarkable pace, with myriad
applications under development. Unlike most earlier machine learning models, they are no …
applications under development. Unlike most earlier machine learning models, they are no …
Robustness, security, privacy, explainability, efficiency, and usability of large language models for code
Large language models for code (LLM4Code), which demonstrate strong performance (eg,
high accuracy) in processing source code, have significantly transformed software …
high accuracy) in processing source code, have significantly transformed software …
Go static: Contextualized logging statement generation
Logging practices have been extensively investigated to assist developers in writing
appropriate logging statements for documenting software behaviors. Although numerous …
appropriate logging statements for documenting software behaviors. Although numerous …
Greening large language models of code
Large language models of code have shown remarkable effectiveness across various
software engineering tasks. Despite the availability of many cloud services built upon these …
software engineering tasks. Despite the availability of many cloud services built upon these …
Enhancing LLM-Based Coding Tools through Native Integration of IDE-Derived Static Context
Large Language Models (LLMs) have achieved remarkable success in code completion, as
evidenced by their essential roles in developing code assistant services such as Copilot …
evidenced by their essential roles in developing code assistant services such as Copilot …
IRCoCo: Immediate Rewards-Guided Deep Reinforcement Learning for Code Completion
Code completion aims to enhance programming productivity by predicting potential code
based on the current programming context. Recently, pre-trained language models (LMs) …
based on the current programming context. Recently, pre-trained language models (LMs) …
Hotfixing Large Language Models for Cod
Z Yang, D Lo - arXiv preprint arXiv:2408.05727, 2024 - arxiv.org
Large Language Models for Code (LLM4Code) have become an integral part of developers'
workflows, assisting with tasks such as code completion and generation. However, these …
workflows, assisting with tasks such as code completion and generation. However, these …
Efficient and Green Large Language Models for Software Engineering: Vision and the Road Ahead
Large Language Models (LLMs) have recently shown remarkable capabilities in various
software engineering tasks, spurring the rapid development of the Large Language Models …
software engineering tasks, spurring the rapid development of the Large Language Models …
[PDF][PDF] AI-driven Software Development Source Code Quality
BCP KANTEK - is.muni.cz
In recent years, applications of artificial intelligence have seen notable success across
various fields. Large Language Models (LLMs) have particularly found extensive use in the …
various fields. Large Language Models (LLMs) have particularly found extensive use in the …