Toward a Theory of Causation for Interpreting Neural Code Models

February 07, 2023 Β· Declared Dead Β· πŸ› IEEE Transactions on Software Engineering

πŸ‘» CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors David N. Palacio, Alejandro Velasco, Nathan Cooper, Alvaro Rodriguez, Kevin Moran, Denys Poshyvanyk arXiv ID 2302.03788 Category cs.SE: Software Engineering Cross-listed cs.AI, cs.LG, stat.ME Citations 24 Venue IEEE Transactions on Software Engineering Last Checked 4 months ago
Abstract
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 $do_{code}$, a post hoc interpretability method specific to NCMs that is capable of explaining model predictions. $do_{code}$ is based upon causal inference to enable programming language-oriented explanations. While the theoretical underpinnings of $do_{code}$ are extensible to exploring different model properties, we provide a concrete instantiation that aims to mitigate the impact of spurious correlations by grounding explanations of model behavior in properties of programming languages. To demonstrate the practical benefit of $do_{code}$, we illustrate the insights that our framework can provide by performing a case study on two popular deep learning architectures and ten NCMs. The results of this case study illustrate that our studied NCMs are sensitive to changes in code syntax. All our NCMs, except for the BERT-like model, statistically learn to predict tokens related to blocks of code (\eg brackets, parenthesis, semicolon) with less confounding bias as compared to other programming language constructs. These insights demonstrate the potential of $do_{code}$ as a useful method to detect and facilitate the elimination of confounding bias in NCMs.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

πŸ“œ Similar Papers

In the same crypt β€” Software Engineering

Died the same way β€” πŸ‘» Ghosted