Code Execution with Pre-trained Language Models

Understand

Code execution is a fundamental aspect of programming language semantics that reflects the exact behavior of the code.

• However, most pre-trained models for code intelligence ignore the execution trace and only rely on source code and syntactic structures.
• In this paper, we investigate how well pre-trained models can understand and perform code execution.
• We develop a mutation-based data augmentation technique to create a large-scale and realistic Python dataset and task for code execution, which challenges existing models such as Codex.