This paper explores the limits of the current generation of large language models for
program synthesis in general purpose programming languages. We evaluate a collection of …

Large language models (LMs) of code have recently shown tremendous promise in
completing code and synthesizing code from natural language descriptions. However, the …

An increasingly popular set of techniques adopted by software engineering (SE)
researchers to automate development tasks are those rooted in the concept of Deep …

Benchmark datasets have a significant impact on accelerating research in programming
language tasks. In this paper, we introduce CodeXGLUE, a benchmark dataset to foster …

Software vulnerabilities are prevalent in software systems, causing a variety of problems
including deadlock, information loss, or system failures. Thus, early predictions of software …

Unit tests play a key role in ensuring the correctness of software. However, manually
creating unit tests is a laborious task, motivating the need for automation. Large Language …

Software systems often record important runtime information in system logs for
troubleshooting purposes. There have been many studies that use log data to construct …

As software vulnerabilities grow in volume and complexity, researchers proposed various
Artificial Intelligence (AI)-based approaches to help under-resourced security analysts to …

Pre-trained models of code have achieved success in many important software engineering
tasks. However, these powerful models are vulnerable to adversarial attacks that slightly …

Code completion is one of the most useful features in the Integrated Development
Environments (IDEs), which can accelerate software development by suggesting the next …