Programmers with LLM access solved fewer formally verified debugging tasks than a no-AI control group, though complete novices and strong language experts gained some benefit.
Proceedings of the ACM on Programming Languages 7(OOPSLA1), 85–111 (2023)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.SE 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Do AI models help produce verified bug fixes?
Programmers with LLM access solved fewer formally verified debugging tasks than a no-AI control group, though complete novices and strong language experts gained some benefit.