LLMs reach moderate macro-F1 scores of 0.36-0.37 when classifying code review comments into six smells and three useful intents, with one-shot examples helping some models on intent labels.
Carver, Christian Bird, Jonathan Orbeck, and Christopher Chockley
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
2026 1verdicts
UNVERDICTED 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Automated Classification of Human Code Review Comments with Large Language Models
LLMs reach moderate macro-F1 scores of 0.36-0.37 when classifying code review comments into six smells and three useful intents, with one-shot examples helping some models on intent labels.