A two-stage detector-plus-LLM-fixer trained on a new, LLM-filtered dataset reports state-of-the-art code-comment inconsistency detection (F1 89.54%) and 18.84% relative GLEU gain in repair.
Classifying code comments in java software systems,
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
support 1representative citing papers
citing papers explorer
-
CCISolver: End-to-End Detection and Repair of Method-Level Code-Comment Inconsistency
A two-stage detector-plus-LLM-fixer trained on a new, LLM-filtered dataset reports state-of-the-art code-comment inconsistency detection (F1 89.54%) and 18.84% relative GLEU gain in repair.