Desiview identifies desired review comments from code review datasets using the perplexity difference of the actual fix with and without each comment, and the distilled data improves LLaMA-based code review models.
An exploratory study of the pull-based software development model,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SE 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Distilling Desired Comments for Enhanced Code Review with Large Language Models
Desiview identifies desired review comments from code review datasets using the perplexity difference of the actual fix with and without each comment, and the distilled data improves LLaMA-based code review models.