DeepCRCEval: Revisiting the Evaluation of Code Review Comment Generation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916583761248256 |
|---|---|
| author | Lu, Junyi Li, Xiaojia Hua, Zihan Yu, Lei Cheng, Shiqi Yang, Li Zhang, Fengjun Zuo, Chun |
| author_facet | Lu, Junyi Li, Xiaojia Hua, Zihan Yu, Lei Cheng, Shiqi Yang, Li Zhang, Fengjun Zuo, Chun |
| contents | Code review is a vital but demanding aspect of software development, generating significant interest in automating review comments. Traditional evaluation methods for these comments, primarily based on text similarity, face two major challenges: inconsistent reliability of human-authored comments in open-source projects and the weak correlation of text similarity with objectives like enhancing code quality and detecting defects.
This study empirically analyzes benchmark comments using a novel set of criteria informed by prior research and developer interviews. We then similarly revisit the evaluation of existing methodologies. Our evaluation framework, DeepCRCEval, integrates human evaluators and Large Language Models (LLMs) for a comprehensive reassessment of current techniques based on the criteria set. Besides, we also introduce an innovative and efficient baseline, LLM-Reviewer, leveraging the few-shot learning capabilities of LLMs for a target-oriented comparison.
Our research highlights the limitations of text similarity metrics, finding that less than 10% of benchmark comments are high quality for automation. In contrast, DeepCRCEval effectively distinguishes between high and low-quality comments, proving to be a more reliable evaluation mechanism. Incorporating LLM evaluators into DeepCRCEval significantly boosts efficiency, reducing time and cost by 88.78% and 90.32%, respectively. Furthermore, LLM-Reviewer demonstrates significant potential of focusing task real targets in comment generation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_18291 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | DeepCRCEval: Revisiting the Evaluation of Code Review Comment Generation Lu, Junyi Li, Xiaojia Hua, Zihan Yu, Lei Cheng, Shiqi Yang, Li Zhang, Fengjun Zuo, Chun Software Engineering Artificial Intelligence Computation and Language Machine Learning Code review is a vital but demanding aspect of software development, generating significant interest in automating review comments. Traditional evaluation methods for these comments, primarily based on text similarity, face two major challenges: inconsistent reliability of human-authored comments in open-source projects and the weak correlation of text similarity with objectives like enhancing code quality and detecting defects. This study empirically analyzes benchmark comments using a novel set of criteria informed by prior research and developer interviews. We then similarly revisit the evaluation of existing methodologies. Our evaluation framework, DeepCRCEval, integrates human evaluators and Large Language Models (LLMs) for a comprehensive reassessment of current techniques based on the criteria set. Besides, we also introduce an innovative and efficient baseline, LLM-Reviewer, leveraging the few-shot learning capabilities of LLMs for a target-oriented comparison. Our research highlights the limitations of text similarity metrics, finding that less than 10% of benchmark comments are high quality for automation. In contrast, DeepCRCEval effectively distinguishes between high and low-quality comments, proving to be a more reliable evaluation mechanism. Incorporating LLM evaluators into DeepCRCEval significantly boosts efficiency, reducing time and cost by 88.78% and 90.32%, respectively. Furthermore, LLM-Reviewer demonstrates significant potential of focusing task real targets in comment generation. |
| title | DeepCRCEval: Revisiting the Evaluation of Code Review Comment Generation |
| topic | Software Engineering Artificial Intelligence Computation and Language Machine Learning |
| url | https://arxiv.org/abs/2412.18291 |