Distilled GPT for source code summarization

CY Su, C McMillan - Automated Software Engineering, 2024‏ - Springer
A code summary is a brief natural language description of source code. Summaries are
usually only a single sentence long, and yet form the backbone of developer documentation …

A closer look into transformer-based code intelligence through code transformation: Challenges and opportunities

Y Li, S Qi, C Gao, Y Peng, D Lo, Z Xu… - arxiv preprint arxiv …, 2022‏ - arxiv.org
Transformer-based models have demonstrated state-of-the-art performance in many
intelligent coding tasks such as code comment generation and code completion. Previous …

Automatic smart contract comment generation via large language models and in-context learning

J Zhao, X Chen, G Yang, Y Shen - Information and Software Technology, 2024‏ - Elsevier
Context: Designing effective automatic smart contract comment generation approaches can
facilitate developers' comprehension, boosting smart contract development and improving …

Where Are Large Language Models for Code Generation on GitHub?

X Yu, L Liu, X Hu, JW Keung, J Liu, X **a - arxiv preprint arxiv:2406.19544, 2024‏ - arxiv.org
The increasing use of Large Language Models (LLMs) in software development has
garnered significant attention from researchers assessing the quality of the code they …

Bashexplainer: Retrieval-augmented bash code comment generation based on fine-tuned codebert

C Yu, G Yang, X Chen, K Liu… - 2022 IEEE International …, 2022‏ - ieeexplore.ieee.org
Developers use shell commands for many tasks, such as file system management, network
control, and process management. Bash is one of the most commonly used shells and plays …

Automatic bi-modal question title generation for Stack Overflow with prompt learning

S Yang, X Chen, K Liu, G Yang, C Yu - Empirical Software Engineering, 2024‏ - Springer
When drafting question posts for Stack Overflow, developers may not accurately summarize
the core problems in the question titles, which can cause these questions to not get timely …

Deep representation learning: Fundamentals, technologies, applications, and open challenges

A Payandeh, KT Baghaei, P Fayyazsanavi… - IEEE …, 2023‏ - ieeexplore.ieee.org
Machine learning algorithms have had a profound impact on the field of computer science
over the past few decades. The performance of these algorithms heavily depends on the …

Understanding the Robustness of Transformer-Based Code Intelligence via Code Transformation: Challenges and Opportunities

Y Li, S Qi, C Gao, Y Peng, D Lo… - IEEE Transactions on …, 2025‏ - ieeexplore.ieee.org
Transformer-based models have demonstrated state-of-the-art performance in various
intelligent coding tasks such as code comment generation and code completion. Previous …

Learning to parallelize in a shared-memory environment with transformers

R Harel, Y Pinter, G Oren - Proceedings of the 28th ACM SIGPLAN …, 2023‏ - dl.acm.org
In past years, the world has switched to multi and many core shared memory architectures.
As a result, there is a growing need to utilize these architectures by introducing shared …

Automated question title reformulation by mining modification logs from stack overflow

K Liu, X Chen, C Chen, X **e… - IEEE Transactions on …, 2023‏ - ieeexplore.ieee.org
In Stack Overflow, developers may not clarify and summarize the critical problems in the
question titles due to a lack of domain knowledge or poor writing skills. Previous studies …