@inproceedings{dau-etal-2024-docchecker,
title = "{D}oc{C}hecker: Bootstrapping Code Large Language Model for Detecting and Resolving Code-Comment Inconsistencies",
author = "Dau, Anh and
Guo, Jin L.c. and
Bui, Nghi",
editor = "Aletras, Nikolaos and
De Clercq, Orphee",
booktitle = "Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations",
month = mar,
year = "2024",
address = "St. Julians, Malta",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.eacl-demo.20",
pages = "187--194",
abstract = "Comments in source code are crucial for developers to understand the purpose of the code and to use it correctly. However, keeping comments aligned with the evolving codebase poses a significant challenge. With increasing interest in automated solutions to identify and rectify discrepancies between code and its associated comments, most existing methods rely heavily on heuristic rules. This paper introduces DocChecker, a language model-based framework adept at detecting inconsistencies between code and comments and capable of generating synthetic comments. This functionality allows DocChecker to identify and rectify cases where comments do not accurately represent the code they describe.The efficacy of DocChecker is demonstrated using the Just-In-Time and CodeXGlue datasets in various scenarios. Notably, DocChecker sets a new benchmark in the Inconsistency Code-Comment Detection (ICCD) task, achieving 72.3{\%} accuracy, and scoring 33.64 in BLEU-4 on the code summarization task. These results surpass other Large Language Models (LLMs), including GPT 3.5 and CodeLlama.DocChecker is accessible for use and evaluation. It can be found on https://github.com/FSoft-AI4Code/DocChecker and at http://4.193.50.237:5000/. For a more comprehensive understanding of its functionality, a demonstration video is available on https://youtu.be/FqnPmd531xw.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dau-etal-2024-docchecker">
<titleInfo>
<title>DocChecker: Bootstrapping Code Large Language Model for Detecting and Resolving Code-Comment Inconsistencies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anh</namePart>
<namePart type="family">Dau</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jin</namePart>
<namePart type="given">L.c.</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nghi</namePart>
<namePart type="family">Bui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nikolaos</namePart>
<namePart type="family">Aletras</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Orphee</namePart>
<namePart type="family">De Clercq</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">St. Julians, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Comments in source code are crucial for developers to understand the purpose of the code and to use it correctly. However, keeping comments aligned with the evolving codebase poses a significant challenge. With increasing interest in automated solutions to identify and rectify discrepancies between code and its associated comments, most existing methods rely heavily on heuristic rules. This paper introduces DocChecker, a language model-based framework adept at detecting inconsistencies between code and comments and capable of generating synthetic comments. This functionality allows DocChecker to identify and rectify cases where comments do not accurately represent the code they describe.The efficacy of DocChecker is demonstrated using the Just-In-Time and CodeXGlue datasets in various scenarios. Notably, DocChecker sets a new benchmark in the Inconsistency Code-Comment Detection (ICCD) task, achieving 72.3% accuracy, and scoring 33.64 in BLEU-4 on the code summarization task. These results surpass other Large Language Models (LLMs), including GPT 3.5 and CodeLlama.DocChecker is accessible for use and evaluation. It can be found on https://github.com/FSoft-AI4Code/DocChecker and at http://4.193.50.237:5000/. For a more comprehensive understanding of its functionality, a demonstration video is available on https://youtu.be/FqnPmd531xw.</abstract>
<identifier type="citekey">dau-etal-2024-docchecker</identifier>
<location>
<url>https://aclanthology.org/2024.eacl-demo.20</url>
</location>
<part>
<date>2024-03</date>
<extent unit="page">
<start>187</start>
<end>194</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DocChecker: Bootstrapping Code Large Language Model for Detecting and Resolving Code-Comment Inconsistencies
%A Dau, Anh
%A Guo, Jin L.c.
%A Bui, Nghi
%Y Aletras, Nikolaos
%Y De Clercq, Orphee
%S Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations
%D 2024
%8 March
%I Association for Computational Linguistics
%C St. Julians, Malta
%F dau-etal-2024-docchecker
%X Comments in source code are crucial for developers to understand the purpose of the code and to use it correctly. However, keeping comments aligned with the evolving codebase poses a significant challenge. With increasing interest in automated solutions to identify and rectify discrepancies between code and its associated comments, most existing methods rely heavily on heuristic rules. This paper introduces DocChecker, a language model-based framework adept at detecting inconsistencies between code and comments and capable of generating synthetic comments. This functionality allows DocChecker to identify and rectify cases where comments do not accurately represent the code they describe.The efficacy of DocChecker is demonstrated using the Just-In-Time and CodeXGlue datasets in various scenarios. Notably, DocChecker sets a new benchmark in the Inconsistency Code-Comment Detection (ICCD) task, achieving 72.3% accuracy, and scoring 33.64 in BLEU-4 on the code summarization task. These results surpass other Large Language Models (LLMs), including GPT 3.5 and CodeLlama.DocChecker is accessible for use and evaluation. It can be found on https://github.com/FSoft-AI4Code/DocChecker and at http://4.193.50.237:5000/. For a more comprehensive understanding of its functionality, a demonstration video is available on https://youtu.be/FqnPmd531xw.
%U https://aclanthology.org/2024.eacl-demo.20
%P 187-194
Markdown (Informal)
[DocChecker: Bootstrapping Code Large Language Model for Detecting and Resolving Code-Comment Inconsistencies](https://aclanthology.org/2024.eacl-demo.20) (Dau et al., EACL 2024)
ACL