Book
Open access
Jul 2026
Assessing Harmful Comments and Specificity in Code Review Feedback at Scale using Large Language Models
This study investigates how large language models can assess code review feedback quality along two dimensions, sentiment and specificity, to support more constructive collaboration, and demonstrates the feasibility and practical utility of automated feedback-quality assessment in real-world environments.
Audrey You, J. Wang, You-Xiang Lei et al.
· SIGSOFT FSE Companion · 0 citations