@inproceedings{duan-etal-2026-automated,
title = "Automated Knowledge Component Generation and Interpretable Knowledge Tracing in Coding Problems",
author = "Duan, Zhangqi and
Fernandez, Nigel and
Lekshmi Narayanan, Arun Balajiee and
Hassany, Mohammad and
de Alencar, Rafaella Sampaio and
Brusilovsky, Peter and
Akram, Bita and
Lan, Andrew",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-acl.1670/",
pages = "33405--33423",
ISBN = "979-8-89176-395-1",
abstract = "Knowledge components (KCs) are key to assessing student knowledge levels on fine-grained skills and driving personalization and feedback. However, crafting KCs and tagging them for problems, traditionally performed by human domain experts, is highly labor-intensive. Prior work has studied automated KC generation only for multiple-choice questions but not open-ended ones. We bridge this gap and present an automated, large language model (LLM)-based pipeline for KC generation and tagging for open-ended programming problems. We also develop an LLM-based knowledge tracing (KT) framework to leverage these LLM-generated KCs. We conduct extensive quantitative and qualitative evaluations on two real-world student code submission datasets. Results show that our KT method outperforms existing ones and LLM-generated KCs outperform human-written KCs on future student response prediction. We also investigate how these KCs enable us to analyze student learning curves and conduct human evaluation with course instructors to further verify the quality of KC-problem tagging."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="duan-etal-2026-automated">
<titleInfo>
<title>Automated Knowledge Component Generation and Interpretable Knowledge Tracing in Coding Problems</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhangqi</namePart>
<namePart type="family">Duan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nigel</namePart>
<namePart type="family">Fernandez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arun</namePart>
<namePart type="given">Balajiee</namePart>
<namePart type="family">Lekshmi Narayanan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="family">Hassany</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rafaella</namePart>
<namePart type="given">Sampaio</namePart>
<namePart type="family">de Alencar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peter</namePart>
<namePart type="family">Brusilovsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bita</namePart>
<namePart type="family">Akram</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrew</namePart>
<namePart type="family">Lan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-395-1</identifier>
</relatedItem>
<abstract>Knowledge components (KCs) are key to assessing student knowledge levels on fine-grained skills and driving personalization and feedback. However, crafting KCs and tagging them for problems, traditionally performed by human domain experts, is highly labor-intensive. Prior work has studied automated KC generation only for multiple-choice questions but not open-ended ones. We bridge this gap and present an automated, large language model (LLM)-based pipeline for KC generation and tagging for open-ended programming problems. We also develop an LLM-based knowledge tracing (KT) framework to leverage these LLM-generated KCs. We conduct extensive quantitative and qualitative evaluations on two real-world student code submission datasets. Results show that our KT method outperforms existing ones and LLM-generated KCs outperform human-written KCs on future student response prediction. We also investigate how these KCs enable us to analyze student learning curves and conduct human evaluation with course instructors to further verify the quality of KC-problem tagging.</abstract>
<identifier type="citekey">duan-etal-2026-automated</identifier>
<location>
<url>https://aclanthology.org/2026.findings-acl.1670/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>33405</start>
<end>33423</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Automated Knowledge Component Generation and Interpretable Knowledge Tracing in Coding Problems
%A Duan, Zhangqi
%A Fernandez, Nigel
%A Lekshmi Narayanan, Arun Balajiee
%A Hassany, Mohammad
%A de Alencar, Rafaella Sampaio
%A Brusilovsky, Peter
%A Akram, Bita
%A Lan, Andrew
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Findings of the Association for Computational Linguistics: ACL 2026
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-395-1
%F duan-etal-2026-automated
%X Knowledge components (KCs) are key to assessing student knowledge levels on fine-grained skills and driving personalization and feedback. However, crafting KCs and tagging them for problems, traditionally performed by human domain experts, is highly labor-intensive. Prior work has studied automated KC generation only for multiple-choice questions but not open-ended ones. We bridge this gap and present an automated, large language model (LLM)-based pipeline for KC generation and tagging for open-ended programming problems. We also develop an LLM-based knowledge tracing (KT) framework to leverage these LLM-generated KCs. We conduct extensive quantitative and qualitative evaluations on two real-world student code submission datasets. Results show that our KT method outperforms existing ones and LLM-generated KCs outperform human-written KCs on future student response prediction. We also investigate how these KCs enable us to analyze student learning curves and conduct human evaluation with course instructors to further verify the quality of KC-problem tagging.
%U https://aclanthology.org/2026.findings-acl.1670/
%P 33405-33423
Markdown (Informal)
[Automated Knowledge Component Generation and Interpretable Knowledge Tracing in Coding Problems](https://aclanthology.org/2026.findings-acl.1670/) (Duan et al., Findings 2026)
ACL
- Zhangqi Duan, Nigel Fernandez, Arun Balajiee Lekshmi Narayanan, Mohammad Hassany, Rafaella Sampaio de Alencar, Peter Brusilovsky, Bita Akram, and Andrew Lan. 2026. Automated Knowledge Component Generation and Interpretable Knowledge Tracing in Coding Problems. In Findings of the Association for Computational Linguistics: ACL 2026, pages 33405–33423, San Diego, California, United States. Association for Computational Linguistics.