Large language models for code (LLM4Code), which demonstrate strong performance (eg,
high accuracy) in processing source code, have significantly transformed software …

For decades, much software engineering research has been dedicated to devising
automated solutions aimed at enhancing developer productivity and elevating software …

Language models for code (CodeLMs) have emerged as powerful tools for code-related
tasks, outperforming traditional methods and standard machine learning approaches …

State-of-the-art source code classification models exhibit excellent task transferability, in
which the source code encoders are first pre-trained on a source domain dataset in a self …

Code models have made significant advancements in code intelligence by encoding
knowledge about programming languages. While previous studies have explored the …

With the widespread application of deep learning in software engineering, deep code
models have played an important role in improving code quality and development efficiency …

This paper introduces a novel method, called WheaCha, for explaining the predictions of
code models. Similar to attribution methods, WheaCha seeks to identify input features that …

Neural code models have demonstrated their efficacy across a range of code
comprehension tasks, including vulnerability detection, code classification, automatic code …

Modern large language models (LLMs), such as ChatGPT, have demonstrated impressive
capabilities for coding tasks including writing and reasoning about code. They improve upon …

This paper tackles the challenge of teaching code semantics to Large Language Models
(LLMs) for program analysis by incorporating code symmetries into the model architecture …