相关论文: Learning code summarization from a small and local…

Source code clones pose risks ranging from intellectual property violations to unintended vulnerabilities. Effective and efficient scalable clone detection, especially for diverged clones, remains challenging. Large language models (LLMs)…

Pre-trained models for Natural Languages (NL) like BERT and GPT have been recently shown to transfer well to Programming Languages (PL) and largely benefit a broad set of code-related tasks. Despite their success, most current methods…

Code optimization is the process of enhancing code efficiency, while preserving its intended functionality. This process often requires a deep understanding of the code execution behavior at run-time to identify and address inefficiencies…

Software vulnerabilities pose significant security threats, requiring effective mitigation. While Automated Program Repair (APR) has advanced in fixing general bugs, vulnerability patching, a security-critical aspect of APR remains…

Language models achieve impressive performance on a variety of knowledge, language, and reasoning tasks due to the scale and diversity of pretraining data available. The standard training recipe is a two-stage paradigm: pretraining first on…

Large language models (LLMs) pretrained on vast source code have achieved prominent progress in code intelligence. However, existing code LLMs have two main limitations in terms of architecture and pretraining tasks. First, they often adopt…

Self-supervised pre-training of transformer models has shown enormous success in improving performance on a number of downstream tasks. However, fine-tuning on a new task still requires large amounts of task-specific labelled data to…

Optimization problems are ubiquitous in our societies and are present in almost every segment of the economy. Most of these optimization problems are NP-hard and computationally demanding, often requiring approximate solutions for…

Code representation learning, which aims to encode the semantics of source code into distributed vectors, plays an important role in recent deep-learning-based models for code intelligence. Recently, many pre-trained language models for…

Matching binary to source code and vice versa has various applications in different fields, such as computer security, software engineering, and reverse engineering. Even though there exist methods that try to match source code with binary…

Tokenization is a fundamental component of language models for code. It involves breaking down the input into units that are later passed to the language model stack to learn high-dimensional representations used in various contexts, from…

In this paper, we propose a context-aware recommender system that models students' programming skills using embeddings of the source code they submit throughout a course. These embeddings predict students' skills across multiple programming…

Software engineering activities frequently involve edits to existing code. However, contemporary code language models (LMs) lack the ability to handle diverse types of code-edit requirements. In this work, we attempt to overcome this…

Large language models (LLMs) have made significant strides at code generation through improved model design, training, and chain-of-thought. However, prompt-level optimizations remain an important yet under-explored aspect of LLMs for…

Code completion is a popular software development tool integrated into all major IDEs. Many neural language models have achieved promising results in completion suggestion prediction on synthetic benchmarks. However, a recent study When…

Source code summarization of a subroutine is the task of writing a short, natural language description of that subroutine. The description usually serves in documentation aimed at programmers, where even brief phrase (e.g. "compresses data…

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…

Understanding source code is a topic of great interest in the software engineering community, since it can help programmers in various tasks such as software maintenance and reuse. Recent advances in large language models (LLMs) have…

Recent studies have adopted pre-trained language models, such as CodeT5 and CodeGPT, for automated program generation tasks like code generation, repair, and translation. Numerous language model-based approaches have been proposed and…

Transformer based code models have impressive performance in many software engineering tasks. However, their effectiveness degrades when symbols are missing or not informative. The reason is that the model may not learn to pay attention to…