Toward a Theory of Causation for Interpreting Neural Code Models

arXiv:2302.03788v2 Announce Type: replace-cross
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. …

abstract arxiv automated capabilities causation code commercial cs.ai cs.lg cs.se developer however language language models limitations metrics research stat.me theory tools type understanding