In this work, we evaluate 10 open-source instructed LLMs on four representative code
comprehension and generation tasks. We have the following main findings. First, for the zero …

The advent of large language models (LLMs) has opened up new opportunities for
automated program repair (APR). In particular, some recent studies have explored how to …

The availability of large-scale datasets, advanced architectures, and powerful computational
resources have led to effective code models that automate diverse software engineering …

In this work we systematically review the recent advancements in code processing with
language models, covering 50+ models, 30+ evaluation tasks, 170+ datasets, and 700 …

SMT solvers are utilized to check the satisfiability of logic formulas and have been applied in
various crucial domains, including software verification, test case generation, and program …

Software Engineering (SE) is the systematic design, development, and maintenance of
software applications, underpinning the digital infrastructure of our modern mainworld. Very …

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

Learning-based techniques, especially advanced Large Language Models (LLMs) for code,
have gained considerable popularity in various software engineering (SE) tasks. However …

Automated code generation has been extensively studied in recent literature. In this work,
we first survey 66 participants to motivate a more pragmatic code generation scenario, ie …

In recent years, large pre-trained Language Models of Code (CodeLMs) have shown
promising results on various software engineering tasks. One such task is automatic code …