Related papers: On the Generalizability of Deep Learning-based Cod…

Deep Learning (DL) models have been widely used to support code completion. These models, once properly trained, can take as input an incomplete code component (e.g., an incomplete function) and predict the missing tokens to finalize it.…

Code security and usability are both essential for various coding assistant applications driven by large language models (LLMs). Current code security benchmarks focus solely on single evaluation task and paradigm, such as code completion…

Large language models (LLMs) have shown promise for automated source-code translation, a capability critical to software migration, maintenance, and interoperability. Yet comparative evidence on how model choice, prompt design, and prompt…

Recent advancements in large language models (LLMs) have significantly enhanced their coding capabilities. However, existing benchmarks predominantly focused on simplified or isolated aspects of coding, such as single-file code generation…

Deep learning has introduced significant improvements in many software analysis tasks. Although the Large Language Models (LLMs) based neural code models demonstrate commendable performance when trained and tested within the intra-project…

Large language models (LLMs) have demonstrated remarkable abilities in representation learning for program synthesis and understanding tasks. The quality of the learned representations appears to be dictated by the neural scaling laws as a…

Test-driven development (TDD) has been adopted to improve Large Language Model (LLM)-based code generation by using tests as executable specifications. However, existing TDD-style code generation studies are largely limited to…

The automated program repair field has attracted substantial interest over the years, but despite significant research efforts, creating a system that works well for complex semantic bugs such as security vulnerabilities has proven…

Large foundation models are fundamentally transforming the software engineering landscape, demonstrating exceptional capabilities across diverse tasks such as code generation, debugging, and testing. Despite this rapid progress, a…

Code generation aims to automatically generate code snippets of specific programming language according to natural language descriptions. The continuous advancements in deep learning, particularly pre-trained models, have empowered the code…

Automatically predicting how difficult it is for humans to understand a code snippet can assist developers in tasks like deciding when and where to refactor. Despite many proposed code comprehensibility metrics, studies have shown they…

Code completion aims to enhance programming productivity by predicting potential code based on the current programming context. Recently, pretrained language models (LMs) have become prominent in this field. Various approaches have been…

The practice of programming is undergoing a revolution with the introduction of AI assisted development (copilots) and the creation of new programming languages that are designed explicitly for tooling, analysis, and automation. Integrated…

In the evolving landscape of large language models (LLMs) tailored for software engineering, the need for benchmarks that accurately reflect real-world development scenarios is paramount. Current benchmarks are either too simplistic or fail…

Fast machine code generation is especially important for fast start-up just-in-time compilation, where the compilation time is part of the end-to-end latency. However, widely used compiler frameworks like LLVM do not prioritize fast…

The rapid proliferation of diverse programming languages presents both opportunities and challenges for developing multilingual code LLMs. While existing techniques often train code LLMs by simply aggregating multilingual code data, few…

With the unprecedented advancements in Large Language Models (LLMs), their application domains have expanded to include code generation tasks across various programming languages. While significant progress has been made in enhancing LLMs…

Code Large Language Models (Code LLMs) are being increasingly employed in real-life applications, so evaluating them is critical. While the conventional accuracy evaluates the performance of Code LLMs on a set of individual tasks, their…

Currently, large pre-trained language models are widely applied in neural code completion systems. Though large code models significantly outperform their smaller counterparts, around 70\% of displayed code completions from Github Copilot…

Automated program repair using neural models has shown promising results on benchmark datasets, yet practical deployment remains limited. In this study, we examine whether a small transformer model can meaningfully repair real-world Java…