@inproceedings{macke-doyle-2024-testing,
title = "Testing the Effect of Code Documentation on Large Language Model Code Understanding",
author = "Macke, William and
Doyle, Michael",
editor = "Duh, Kevin and
Gomez, Helena and
Bethard, Steven",
booktitle = "Findings of the Association for Computational Linguistics: NAACL 2024",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-naacl.66",
pages = "1044--1050",
abstract = "Large Language Models (LLMs) have demonstrated impressive abilities in recent years with regards to code generation and understanding. However, little work has investigated how documentation and other code properties affect an LLM{'}s ability to understand and generate code or documentation. We present an empirical analysis of how underlying properties of code or documentation can affect an LLM{'}s capabilities. We show that providing an LLM with {``}incorrect{''} documentation can greatly hinder code understanding, while incomplete or missing documentation does not seem to significantly affect an LLM{'}s ability to understand code.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="macke-doyle-2024-testing">
<titleInfo>
<title>Testing the Effect of Code Documentation on Large Language Model Code Understanding</title>
</titleInfo>
<name type="personal">
<namePart type="given">William</namePart>
<namePart type="family">Macke</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Doyle</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: NAACL 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Duh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helena</namePart>
<namePart type="family">Gomez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Large Language Models (LLMs) have demonstrated impressive abilities in recent years with regards to code generation and understanding. However, little work has investigated how documentation and other code properties affect an LLM’s ability to understand and generate code or documentation. We present an empirical analysis of how underlying properties of code or documentation can affect an LLM’s capabilities. We show that providing an LLM with “incorrect” documentation can greatly hinder code understanding, while incomplete or missing documentation does not seem to significantly affect an LLM’s ability to understand code.</abstract>
<identifier type="citekey">macke-doyle-2024-testing</identifier>
<location>
<url>https://aclanthology.org/2024.findings-naacl.66</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>1044</start>
<end>1050</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Testing the Effect of Code Documentation on Large Language Model Code Understanding
%A Macke, William
%A Doyle, Michael
%Y Duh, Kevin
%Y Gomez, Helena
%Y Bethard, Steven
%S Findings of the Association for Computational Linguistics: NAACL 2024
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F macke-doyle-2024-testing
%X Large Language Models (LLMs) have demonstrated impressive abilities in recent years with regards to code generation and understanding. However, little work has investigated how documentation and other code properties affect an LLM’s ability to understand and generate code or documentation. We present an empirical analysis of how underlying properties of code or documentation can affect an LLM’s capabilities. We show that providing an LLM with “incorrect” documentation can greatly hinder code understanding, while incomplete or missing documentation does not seem to significantly affect an LLM’s ability to understand code.
%U https://aclanthology.org/2024.findings-naacl.66
%P 1044-1050
Markdown (Informal)
[Testing the Effect of Code Documentation on Large Language Model Code Understanding](https://aclanthology.org/2024.findings-naacl.66) (Macke & Doyle, Findings 2024)
ACL