@inproceedings{kovalchuk-etal-2025-predictive,
title = "Predictive Modeling of Human Developers' Evaluative Judgment of Generated Code as a Decision Process",
author = "Kovalchuk, Sergey and
Li, Yanyu and
Fedrushkov, Dmitriy",
editor = "Blodgett, Su Lin and
Curry, Amanda Cercas and
Dev, Sunipa and
Li, Siyan and
Madaio, Michael and
Wang, Jack and
Wu, Sherry Tongshuang and
Xiao, Ziang and
Yang, Diyi",
booktitle = "Proceedings of the Fourth Workshop on Bridging Human-Computer Interaction and Natural Language Processing (HCI+NLP)",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.hcinlp-1.10/",
pages = "120--128",
ISBN = "979-8-89176-353-1",
abstract = "The paper presents early results in the development of an approach to predictive modeling of human developer perceiving of code generated in question-answering scenarios with Large Language Model (LLM) applications. The study is focused on building a model for the description and prediction of human implicit behavior during evaluative judgment of generated code through evaluation of its consistency, correctness, and usefulness as subjective perceiving characteristics. We used Markov Decision Process (MDP) as a basic framework to describe the human developer and his/her perceiving. We consider two approaches (regression-based and classification-based) to identify MDP parameters so it can be used as an ``artificial'' developer for human-centered code evaluation. An experimental evaluation of the proposed approach was performed with survey data previously collected for several code generation LLMs in a question-answering scenario. The results show overall good performance of the proposed model in acceptance rate prediction (accuracy 0.82) and give promising perspectives for further development and application."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kovalchuk-etal-2025-predictive">
<titleInfo>
<title>Predictive Modeling of Human Developers’ Evaluative Judgment of Generated Code as a Decision Process</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sergey</namePart>
<namePart type="family">Kovalchuk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yanyu</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dmitriy</namePart>
<namePart type="family">Fedrushkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fourth Workshop on Bridging Human-Computer Interaction and Natural Language Processing (HCI+NLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Su</namePart>
<namePart type="given">Lin</namePart>
<namePart type="family">Blodgett</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amanda</namePart>
<namePart type="given">Cercas</namePart>
<namePart type="family">Curry</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Siyan</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Madaio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jack</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sherry</namePart>
<namePart type="given">Tongshuang</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ziang</namePart>
<namePart type="family">Xiao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Diyi</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-353-1</identifier>
</relatedItem>
<abstract>The paper presents early results in the development of an approach to predictive modeling of human developer perceiving of code generated in question-answering scenarios with Large Language Model (LLM) applications. The study is focused on building a model for the description and prediction of human implicit behavior during evaluative judgment of generated code through evaluation of its consistency, correctness, and usefulness as subjective perceiving characteristics. We used Markov Decision Process (MDP) as a basic framework to describe the human developer and his/her perceiving. We consider two approaches (regression-based and classification-based) to identify MDP parameters so it can be used as an “artificial” developer for human-centered code evaluation. An experimental evaluation of the proposed approach was performed with survey data previously collected for several code generation LLMs in a question-answering scenario. The results show overall good performance of the proposed model in acceptance rate prediction (accuracy 0.82) and give promising perspectives for further development and application.</abstract>
<identifier type="citekey">kovalchuk-etal-2025-predictive</identifier>
<location>
<url>https://aclanthology.org/2025.hcinlp-1.10/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>120</start>
<end>128</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Predictive Modeling of Human Developers’ Evaluative Judgment of Generated Code as a Decision Process
%A Kovalchuk, Sergey
%A Li, Yanyu
%A Fedrushkov, Dmitriy
%Y Blodgett, Su Lin
%Y Curry, Amanda Cercas
%Y Dev, Sunipa
%Y Li, Siyan
%Y Madaio, Michael
%Y Wang, Jack
%Y Wu, Sherry Tongshuang
%Y Xiao, Ziang
%Y Yang, Diyi
%S Proceedings of the Fourth Workshop on Bridging Human-Computer Interaction and Natural Language Processing (HCI+NLP)
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-353-1
%F kovalchuk-etal-2025-predictive
%X The paper presents early results in the development of an approach to predictive modeling of human developer perceiving of code generated in question-answering scenarios with Large Language Model (LLM) applications. The study is focused on building a model for the description and prediction of human implicit behavior during evaluative judgment of generated code through evaluation of its consistency, correctness, and usefulness as subjective perceiving characteristics. We used Markov Decision Process (MDP) as a basic framework to describe the human developer and his/her perceiving. We consider two approaches (regression-based and classification-based) to identify MDP parameters so it can be used as an “artificial” developer for human-centered code evaluation. An experimental evaluation of the proposed approach was performed with survey data previously collected for several code generation LLMs in a question-answering scenario. The results show overall good performance of the proposed model in acceptance rate prediction (accuracy 0.82) and give promising perspectives for further development and application.
%U https://aclanthology.org/2025.hcinlp-1.10/
%P 120-128
Markdown (Informal)
[Predictive Modeling of Human Developers’ Evaluative Judgment of Generated Code as a Decision Process](https://aclanthology.org/2025.hcinlp-1.10/) (Kovalchuk et al., HCINLP 2025)
ACL