相关论文: Towards Identifying Code Proficiency through the A…

The understanding of source code in large-scale software systems poses a challenge for developers. The role of expertise in source code becomes critical for identifying developers accountable for substantial changes. However, in the context…

Large Language Models (LLMs) increasingly exhibit strong reasoning abilities, often attributed to their capacity to generate chain-of-thought-style intermediate reasoning. Recent work suggests that exposure to code can further enhance these…

Within the last years, Python became more prominent in the scientific community and is now used for simulations, machine learning, and data analysis. All these tasks profit from additional compute power offered by parallelism and…

Software developers use Application Programming Interfaces (APIs) of libraries and frameworks extensively while writing programs. In this context, the recommendations provided in code completion pop-ups help developers choose the desired…

Natural language processing for programming aims to use NLP techniques to assist programming. It is increasingly prevalent for its effectiveness in improving productivity. Distinct from natural language, a programming language is highly…

This book is intended for beginners who have no familiarity with deep learning. Our only expectation from readers is that they already have the basic programming skills in Python.

Large Language Models (LLMs) have exhibited exceptional performance in software engineering yet face challenges in adapting to continually evolving code knowledge, particularly regarding the frequent updates of third-party library APIs.…

Large language models possess impressive capabilities in generating programs (e.g., Python) from natural language descriptions to execute robotic tasks. However, these generated programs often contain errors that violate externally given…

Large language models (LLMs) have demonstrated strong performance on function-level code generation benchmarks, yet real-world software development increasingly demands class-level implementations that integrate multiple methods,…

Introduction: Taxonomies capture knowledge about a particular domain in a succinct manner and establish a common understanding among peers. Researchers use taxonomies to convey information about a particular knowledge area or to support…

Large Language Models (LLMs) have achieved state-of-the-art performance across software engineering tasks, from code generation to translation. However, we identify and systematically evaluate a critical failure mode: Programming Language…

While high-level languages come with significant readability and maintainability benefits, their performance remains difficult to predict. For example, programmers may unknowingly use language features inappropriately, which cause their…

Numerical stability is a crucial requirement of reliable scientific computing. However, despite the pervasiveness of Python in data science, analyzing large Python programs remains challenging due to the lack of scalable numerical analysis…

Evaluation of text generation to date has primarily focused on content created sequentially, rather than improvements on a piece of text. Writing, however, is naturally an iterative and incremental process that requires expertise in…

Refactoring, the process of improving the code structure of a software system without altering its behavior, is crucial for managing code evolution in software development. Identifying refactoring actions in source code is essential for…

Comparing the quality of software written in different computer languages is required in a variety of scenarios, e.g. multi-language projects or application selection process among candidates in different languages. We focus on the…

Program comprehension is a fundamental task in software development and maintenance processes. Software developers often need to understand a large amount of existing code before they can develop new features or fix bugs in existing…

Software vulnerabilities are a serious and crucial concern. Typically, in a program or function consisting of hundreds or thousands of source code statements, there are only a few statements causing the corresponding vulnerabilities. Most…

Generative machine learning models have recently been applied to source code, for use cases including translating code between programming languages, creating documentation from code, and auto-completing methods. Yet, state-of-the-art…

Code completion aims to help improve developers' productivity by suggesting the next code tokens from a given context. Various approaches have been proposed to incorporate abstract syntax tree (AST) information for model training, ensuring…