Octopack: Instruction tuning code large language models

N Muennighoff, Q Liu, A Zebaze, Q Zheng… - arXiv preprint arXiv …, 2023 - arxiv.org
Finetuning large language models (LLMs) on instructions leads to vast performance
improvements on natural language tasks. We apply instruction tuning using code …

A code centric evaluation of c/c++ vulnerability datasets for deep learning based vulnerability detection techniques

R Jain, N Gervasoni, M Ndhlovu, S Rawat - Proceedings of the 16th …, 2023 - dl.acm.org
Recent years have witnessed tremendous progress in NLP-based code comprehension via
deep neural networks (DNN) learning, especially Large Language Models (LLMs). While the …

Multi-grained contextual code representation learning for commit message generation

C Wang, L Zhang, X Zhang - Information and Software Technology, 2024 - Elsevier
Commit messages, precisely describing the code changes for each commit in natural
language, makes it possible for developers and succeeding reviewers to understand the …

Summarize Me: The Future of Issue Thread Interpretation

A Kumar, PP Das… - 2023 IEEE International …, 2023 - ieeexplore.ieee.org
Understanding issue threads is an essential aspect of software maintenance and
development, aiding developers in effectively addressing and managing software-related …

Mucha: Multi-channel based Code Change Representation Learning for Commit Message Generation

C Wang, Y Wu, X Zhang - 2023 IEEE 23rd International …, 2023 - ieeexplore.ieee.org
Commit messages provide a natural language description of the changes made to the code,
enabling developers to swiftly comprehend the alterations without delving into the …

Comu: Contextual and Multi-Grained Code Representation Learning for Commit Message Generation

C Wang, L Zhang, X Zhang - Available at SSRN 4511874 - papers.ssrn.com
Commit messages, precisely describing the code changes for each commit in natural
language, makes it possible for developers and succeeding reviewers to understand the …