@inproceedings{cheng-etal-2024-towards,
title = "Towards Explainable Computerized Adaptive Testing with Large Language Model",
author = "Cheng, Cheng and
Zhao, GuanHao and
Huang, Zhenya and
Zhuang, Yan and
Pan, Zhaoyuan and
Liu, Qi and
Li, Xin and
Chen, Enhong",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-emnlp.149",
pages = "2655--2672",
abstract = "As intelligent education evolves, it will provide students with multiple personalized learning services based on their individual abilities. Computerized adaptive testing (CAT) is designed to accurately measure a student{'}s ability using the least questions, providing an efficient and personalized testing method. However, existing methods mainly focus on minimizing the number of questions required to assess ability, often lacking clear and reliable explanations for the question selection process. Educators and students can hardly trust and accept CAT systems without an understanding of the rationale behind the question selection process. To address this issue, we introduce \textbf{L}LM-\textbf{A}gent-Based \textbf{CAT} (LACAT), a novel agent powered by large language models to enhance CAT with human-like interpretability and explanation capabilities. LACAT consists of three key modules: the Summarizer, which generates interpretable student profiles; the Reasoner, which personalizes questions and provides human-readable explanations; and the Critic, which learns from past choices to optimize future question selection. We conducted extensive experiments on three real-world educational datasets. The results demonstrate that LACAT can perform comparably or superior to traditional CAT methods in accuracy and significantly improve the transparency and acceptability of the testing process. Human evaluations further confirm that LACAT can generate high-quality, understandable explanations, thereby enhancing student trust and satisfaction.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cheng-etal-2024-towards">
<titleInfo>
<title>Towards Explainable Computerized Adaptive Testing with Large Language Model</title>
</titleInfo>
<name type="personal">
<namePart type="given">Cheng</namePart>
<namePart type="family">Cheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">GuanHao</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhenya</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yan</namePart>
<namePart type="family">Zhuang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhaoyuan</namePart>
<namePart type="family">Pan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qi</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xin</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enhong</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yaser</namePart>
<namePart type="family">Al-Onaizan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>As intelligent education evolves, it will provide students with multiple personalized learning services based on their individual abilities. Computerized adaptive testing (CAT) is designed to accurately measure a student’s ability using the least questions, providing an efficient and personalized testing method. However, existing methods mainly focus on minimizing the number of questions required to assess ability, often lacking clear and reliable explanations for the question selection process. Educators and students can hardly trust and accept CAT systems without an understanding of the rationale behind the question selection process. To address this issue, we introduce LLM-Agent-Based CAT (LACAT), a novel agent powered by large language models to enhance CAT with human-like interpretability and explanation capabilities. LACAT consists of three key modules: the Summarizer, which generates interpretable student profiles; the Reasoner, which personalizes questions and provides human-readable explanations; and the Critic, which learns from past choices to optimize future question selection. We conducted extensive experiments on three real-world educational datasets. The results demonstrate that LACAT can perform comparably or superior to traditional CAT methods in accuracy and significantly improve the transparency and acceptability of the testing process. Human evaluations further confirm that LACAT can generate high-quality, understandable explanations, thereby enhancing student trust and satisfaction.</abstract>
<identifier type="citekey">cheng-etal-2024-towards</identifier>
<location>
<url>https://aclanthology.org/2024.findings-emnlp.149</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>2655</start>
<end>2672</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Towards Explainable Computerized Adaptive Testing with Large Language Model
%A Cheng, Cheng
%A Zhao, GuanHao
%A Huang, Zhenya
%A Zhuang, Yan
%A Pan, Zhaoyuan
%A Liu, Qi
%A Li, Xin
%A Chen, Enhong
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Findings of the Association for Computational Linguistics: EMNLP 2024
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F cheng-etal-2024-towards
%X As intelligent education evolves, it will provide students with multiple personalized learning services based on their individual abilities. Computerized adaptive testing (CAT) is designed to accurately measure a student’s ability using the least questions, providing an efficient and personalized testing method. However, existing methods mainly focus on minimizing the number of questions required to assess ability, often lacking clear and reliable explanations for the question selection process. Educators and students can hardly trust and accept CAT systems without an understanding of the rationale behind the question selection process. To address this issue, we introduce LLM-Agent-Based CAT (LACAT), a novel agent powered by large language models to enhance CAT with human-like interpretability and explanation capabilities. LACAT consists of three key modules: the Summarizer, which generates interpretable student profiles; the Reasoner, which personalizes questions and provides human-readable explanations; and the Critic, which learns from past choices to optimize future question selection. We conducted extensive experiments on three real-world educational datasets. The results demonstrate that LACAT can perform comparably or superior to traditional CAT methods in accuracy and significantly improve the transparency and acceptability of the testing process. Human evaluations further confirm that LACAT can generate high-quality, understandable explanations, thereby enhancing student trust and satisfaction.
%U https://aclanthology.org/2024.findings-emnlp.149
%P 2655-2672
Markdown (Informal)
[Towards Explainable Computerized Adaptive Testing with Large Language Model](https://aclanthology.org/2024.findings-emnlp.149) (Cheng et al., Findings 2024)
ACL
- Cheng Cheng, GuanHao Zhao, Zhenya Huang, Yan Zhuang, Zhaoyuan Pan, Qi Liu, Xin Li, and Enhong Chen. 2024. Towards Explainable Computerized Adaptive Testing with Large Language Model. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 2655–2672, Miami, Florida, USA. Association for Computational Linguistics.