Do Large Code Models Understand Programming Concepts? A Black Box Approach

Large Language Models have been able to replicate their success from text generation to coding tasks. While a lot of work has made it clear that they have remarkable performance on tasks such as code completion and editing, it is still unclear as to why. We help bridge this gap by exploring to what degree do auto-regressive models understand the logical constructs of the underlying programs. We propose CAPP, a counterfactual testing framework to evaluate whether large code models understand programming concepts. With only black-box access to the model, we use CAPP to evaluate 10 popular large code models for 5 different programming concepts. Our findings suggest that current models lack understanding of concepts such as data flow and control flow.

• Software Systems

• Machine Intelligence