Related papers: CodeS: Towards Code Model Generalization Under Dis…

Code-mixing and code-switching (CSW) remain challenging phenomena for large language models (LLMs). Despite recent advances in multilingual modeling, LLMs often struggle in mixed-language settings, exhibiting systematic degradation in…

Security vulnerabilities present in a code that has been written in diverse programming languages are among the most critical yet complicated aspects of source code to detect. Static analysis tools based on rule-based patterns usually do…

Large language models (LLMs) exhibit remarkable multilingual capabilities despite the extreme language imbalance in the pre-training data. In this paper, we closely examine the reasons behind this phenomenon, focusing on the pre-training…

Code translation between programming languages (PLs) is a critical task in software engineering, facilitating the modernization of legacy systems, ensuring cross-platform compatibility, and enhancing software performance. Most existing…

The rapid rise of Large Language Models (LLMs) has changed software development, with tools like Copilot, JetBrains AI Assistant, and others boosting developers' productivity. However, developers now spend more time reviewing code than…

Although deep learning has shown great success in recent years, researchers have discovered a critical flaw where small, imperceptible changes in the input to the system can drastically change the output classification. These attacks are…

Code intelligence leverages machine learning techniques to extract knowledge from extensive code corpora, with the aim of developing intelligent tools to improve the quality and productivity of computer programming. Currently, there is…

Software is constantly changing, requiring developers to perform several derived tasks in a timely manner, such as writing a description for the intention of the code change, or identifying the defect-prone code changes. Considering that…

Distributional shift, or the mismatch between training and deployment data, is a significant obstacle to the usage of machine learning in high-stakes industrial applications, such as autonomous driving and medicine. This creates a need to…

Code vulnerability detection (CVD) is essential for addressing and preventing system security issues, playing a crucial role in ensuring software security. Previous learning-based vulnerability detection methods rely on either fine-tuning…

In the field of Machine Learning (ML) and data-driven applications, one of the significant challenge is the change in data distribution between the training and deployment stages, commonly known as distribution shift. This paper outlines…

Large language models (LLMs) excel in many tasks of software engineering, yet progress in leveraging them for vulnerability discovery has stalled in recent years. To understand this phenomenon, we investigate LLMs through the lens of…

Despite achieving impressive results on standard benchmarks, large foundational models still struggle against code-switching test cases. When data scarcity cannot be used as the usual justification for poor performance, the reason may lie…

Deep Learning applications are becoming increasingly popular. Developers of deep learning systems strive to write more efficient code. Deep learning systems are constantly evolving, imposing tighter development timelines and increasing…

Coding remains one of the most fundamental modes of interaction between humans and machines. With the rapid advancement of Large Language Models (LLMs), code generation capabilities have begun to significantly reshape programming practices.…

A significant obstacle in the development of robust machine learning models is covariate shift, a form of distribution shift that occurs when the input distributions of the training and test sets differ while the conditional label…

Large models have achieved remarkable performance across various tasks, yet they incur significant computational costs and privacy concerns during both training and inference. Distributed deployment has emerged as a potential solution, but…

Large language models (LLMs) have exerted a considerable impact on diverse language-related tasks in recent years. Their demonstrated state-of-the-art performance is achieved through methodologies such as zero-shot or few-shot prompting.…

Code cloning, the duplication of code fragments, is common in software development. While some reuse aids productivity, excessive cloning hurts maintainability and introduces bugs. Hence, automatic code clone detection is vital. Meanwhile,…

Program representation learning is a fundamental task in software engineering applications. With the availability of "big code" and the development of deep learning techniques, various program representation learning models have been…