Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2023
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2306.06347 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866913221678465024 |
|---|---|
| author | Dau, Anh T. V. Guo, Jin L. C. Bui, Nghi D. Q. |
| author_facet | Dau, Anh T. V. Guo, Jin L. C. Bui, Nghi D. Q. |
| contents | Comments within source code are essential for developers to comprehend the code's purpose and ensure its correct usage. However, as codebases evolve, maintaining an accurate alignment between the comments and the code becomes increasingly challenging. Recognizing the growing interest in automated solutions for detecting and correcting differences between code and its accompanying comments, current methods rely primarily on heuristic rules. In contrast, this paper presents DocChecker, a tool powered by deep learning. DocChecker is adept at identifying inconsistencies between code and comments, and it can also generate synthetic comments. This capability enables the tool to detect and correct instances where comments do not accurately reflect their corresponding code segments. We demonstrate the effectiveness of DocChecker using the Just-In-Time and CodeXGlue datasets in different settings. Particularly, DocChecker achieves a new State-of-the-art result of 72.3% accuracy on the Inconsistency Code-Comment Detection (ICCD) task and 33.64 BLEU-4 on the code summarization task against other Large Language Models (LLMs), even surpassing GPT 3.5 and CodeLlama.
DocChecker is accessible for use and evaluation. It can be found on our GitHub https://github.com/FSoft-AI4Code/DocChecker and as an Online Tool http://4.193.50.237:5000/. For a more comprehensive understanding of its functionality, a demonstration video is available on YouTube https://youtu.be/FqnPmd531xw. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2306_06347 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | DocChecker: Bootstrapping Code Large Language Model for Detecting and Resolving Code-Comment Inconsistencies Dau, Anh T. V. Guo, Jin L. C. Bui, Nghi D. Q. Software Engineering Comments within source code are essential for developers to comprehend the code's purpose and ensure its correct usage. However, as codebases evolve, maintaining an accurate alignment between the comments and the code becomes increasingly challenging. Recognizing the growing interest in automated solutions for detecting and correcting differences between code and its accompanying comments, current methods rely primarily on heuristic rules. In contrast, this paper presents DocChecker, a tool powered by deep learning. DocChecker is adept at identifying inconsistencies between code and comments, and it can also generate synthetic comments. This capability enables the tool to detect and correct instances where comments do not accurately reflect their corresponding code segments. We demonstrate the effectiveness of DocChecker using the Just-In-Time and CodeXGlue datasets in different settings. Particularly, DocChecker achieves a new State-of-the-art result of 72.3% accuracy on the Inconsistency Code-Comment Detection (ICCD) task and 33.64 BLEU-4 on the code summarization task against other Large Language Models (LLMs), even surpassing GPT 3.5 and CodeLlama. DocChecker is accessible for use and evaluation. It can be found on our GitHub https://github.com/FSoft-AI4Code/DocChecker and as an Online Tool http://4.193.50.237:5000/. For a more comprehensive understanding of its functionality, a demonstration video is available on YouTube https://youtu.be/FqnPmd531xw. |
| title | DocChecker: Bootstrapping Code Large Language Model for Detecting and Resolving Code-Comment Inconsistencies |
| topic | Software Engineering |
| url | https://arxiv.org/abs/2306.06347 |