Code-generating large language models map natural language to code. However, only a
small portion of the infinite space of naturalistic utterances is effective at guiding code …

Large language models (LLMs) such as Llama 2 perform very well on tasks that involve both
natural language and source code, particularly code summarization and code generation …

Code pre-trained models (CodePTMs) have recently demonstrated significant success in
code intelligence. To interpret these models, some probing methods have been applied …

In the cloud-native era, developers have at their disposal an unprecedented landscape of
services to build scalable distributed systems. The DevOps paradigm emerged as a …

Learning vector representations for programs is a critical step in applying deep learning
techniques for program understanding tasks. Various neural network models are proposed …

A popular language model that can solve introductory programming problems, OpenAI's
Codex, has drawn much attention not only in the natural language processing field but also …

Transformers are now widely utilized in code intelligence tasks. To better fit highly structured
source code, various structure information is passed into Transformer, such as positional …

The ability of CodeLLMs to generate executable and functionally correct code at the\textit
{repository-level scale} remains largely unexplored. We introduce\methodnamews, a novel …

Recently, Large Langauge Models (LLMs) have gained a lot of attention in the Software
Engineering (SE) community. LLMs or their variants pre-trained on code are used for many …

Large Language Models trained on code corpora (code-LLMs) have demonstrated
impressive performance in various coding assistance tasks. However, despite their …