Related papers: An Exploratory Investigation into Code License Inf…

In light of recent legal allegations brought by publishers, newspapers, and other creators of copyrighted corpora against large language model developers who use their copyrighted materials for training or fine-tuning purposes, we propose a…

General large language models (LLMs), represented by ChatGPT, have demonstrated significant potential in tasks such as code generation in software engineering. This has led to the development of specialized LLMs for software engineering,…

Recent years have witnessed significant progress in developing deep learning-based models for automated code completion. Although using source code in GitHub has been a common practice for training deep-learning-based models for code…

This article presents a study on the quality and execution of research code from publicly-available replication datasets at the Harvard Dataverse repository. Research code is typically created by a group of scientists and published together…

Large language models (LLMs) have revolutionized code generation, automating programming with remarkable efficiency. However, these advancements challenge programming skills, ethics, and assessment integrity, making the detection of…

Language Models (LLMs), such as transformer-based neural networks trained on billions of parameters, have become increasingly prevalent in software engineering (SE). These models, trained on extensive datasets that include code…

API misuse in code generated by large language models (LLMs) presents a serious and growing challenge in software development, as although LLMs demonstrate impressive code generation capabilities, their interactions with complex library…

As large language models (LLMs) rapidly advance, their role in code generation has expanded significantly. While this offers streamlined development, it also creates concerns in areas like education and job interviews. Consequently,…

Modern software relies on a multitude of automated testing and quality assurance tools to prevent errors, bugs and potential vulnerabilities. This study sets out to provide a head-to-head, quantitative and qualitative evaluation of six…

Poisoning attacks can compromise the safety of large language models (LLMs) by injecting malicious documents into their training data. Existing work has studied pretraining poisoning assuming adversaries control a percentage of the training…

Past work has shown that large language models are susceptible to privacy attacks, where adversaries generate sequences from a trained model and detect which sequences are memorized from the training set. In this work, we show that the…

The last decade has seen widespread adoption of Machine Learning (ML) components in software systems. This has occurred in nearly every domain, from natural language processing to computer vision. These ML components range from relatively…

Secure coding is a critical yet often overlooked practice in software development. Despite extensive awareness efforts, real-world adoption remains inconsistent due to organizational, educational, and technical barriers. This paper provides…

Code-related benchmarks play a critical role in evaluating large language models (LLMs), yet their quality fundamentally shapes how the community interprets model capabilities. In the past few years, awareness of benchmark quality has…

Data quality is crucial for training accurate, unbiased, and trustworthy machine learning models as well as for their correct evaluation. Recent works, however, have shown that even popular datasets used to train and evaluate…

Code-switching is a pervasive phenomenon in multilingual communication, yet the robustness of large language models (LLMs) in mixed-language settings remains insufficiently understood. In this work, we present a comprehensive evaluation of…

Generative artificial intelligence attracts significant attention, especially with the introduction of large language models. Its capabilities are being exploited to solve various software engineering tasks. Thanks to their ability to…

Large Language Models (LLMs) have demonstrated remarkable capabilities across a variety of software engineering and coding tasks. However, their application in the domain of code and compiler optimization remains underexplored. Training…

The advancements in machine learning techniques have encouraged researchers to apply these techniques to a myriad of software engineering tasks that use source code analysis, such as testing and vulnerability detection. Such a large number…

Large Language Models (LLMs) have transformed machine learning but raised significant legal concerns due to their potential to produce text that infringes on copyrights, resulting in several high-profile lawsuits. The legal landscape is…