查看文章

Neural Language Models of Code, or Neural Code Models (NCMs), are rapidly progressing from research prototypes to commercial developer tools. As such, understanding the capabilities and limitations of such models is becoming critical. However, the abilities of these models are typically measured using automated metrics that often only reveal a portion of their real-world performance. While, in general, the performance of NCMs appears promising, currently much is unknown about how such models arrive at decisions. To this end, this paper introduces do , a post hoc interpretability method specific to NCMs that is capable of explaining model predictions. do is based upon causal inference to enable programming language-oriented explanations. While the theoretical underpinnings of do are extensible to exploring different model properties, we provide a concrete instantiation that aims to mitigate the impact …