Exploring and unleashing the power of large language models in automated code translation

Z Yang, F Liu, Z Yu, JW Keung, J Li, S Liu… - Proceedings of the …, 2024 - dl.acm.org
Code translation tools, namely transpilers, are developed for automatic source-to-source
translation. Latest learning-based transpilers have shown impressive enhancement against …

TerGEC: A graph enhanced contrastive approach for program termination analysis

S Liu, JW Keung, Z Yang, Y Liao, Y Li - Science of Computer Programming, 2024 - Elsevier
Context Programs with non-termination behavior induce various bugs, such as denial-of-
service vulnerability and memory exhaustion. Hence the ability to detect non-termination …

Understanding Code Changes Practically with Small-Scale Language Models

C Li, Z Xu, P Di, D Wang, Z Li, Q Zheng - Proceedings of the 39th IEEE …, 2024 - dl.acm.org
Recent studies indicate that traditional techniques for understanding code changes are not
as effective as techniques that directly prompt language models (LMs). However, current LM …

An Empirical Study on Learning-based Techniques for Explicit and Implicit Commit Messages Generation

Z Huang, Y Huang, X Chen, X Zhou, C Yang… - Proceedings of the 39th …, 2024 - dl.acm.org
High-quality and appropriate commit messages help developers to quickly understand and
track code evolution, which is crucial for the collaborative development and maintenance of …

RAG-Enhanced Commit Message Generation

L Zhang, H Zhang, C Wang, P Liang - arXiv preprint arXiv:2406.05514, 2024 - arxiv.org
Commit message is one of the most important textual information in software development
and maintenance. However, it is time-consuming and labor-intensive to write commit …

A Methodology for Evaluating RAG Systems: A Case Study On Configuration Dependency Validation

S Simon, A Mailach, J Dorn, N Siegmund - arXiv preprint arXiv …, 2024 - arxiv.org
Retrieval-augmented generation (RAG) is an umbrella of different components, design
decisions, and domain-specific adaptations to enhance the capabilities of large language …

Escalating LLM-based Code Translation Benchmarking into the Class-level Era

P Xue, L Wu, C Wang, X Li, Z Yang, R Jin… - arXiv preprint arXiv …, 2024 - arxiv.org
In recent years, Large Language Models (LLMs) have significantly improved automated
code translation, often achieving over 80% accuracy on existing benchmarks. However …

LLM-Cure: LLM-based Competitor User Review Analysis for Feature Enhancement

M Assi, S Hassan, Y Zou - arXiv preprint arXiv:2409.15724, 2024 - arxiv.org
The exponential growth of the mobile app market underscores the importance of constant
innovation and rapid response to user demands. As user satisfaction is paramount to the …

[PDF][PDF] Machine Learning Driven Guidance for Software Maintenance: Enhancing Code Management and Features

M Assi - 2024 - qspace.library.queensu.ca
Software systems undergo continuous maintenance to fix defects, enhance features, and
improve code quality to ensure that systems stay reliable and relevant in a competitive …