@inproceedings{mucciaccia-etal-2025-automatic,
title = "Automatic Multiple-Choice Question Generation and Evaluation Systems Based on {LLM}: A Study Case With University Resolutions",
author = "Mucciaccia, S{\'e}rgio Silva and
Meireles Paix{\~a}o, Thiago and
Wall Mutz, Filipe and
Santos Badue, Claudine and
Ferreira de Souza, Alberto and
Oliveira-Santos, Thiago",
editor = "Rambow, Owen and
Wanner, Leo and
Apidianaki, Marianna and
Al-Khalifa, Hend and
Eugenio, Barbara Di and
Schockaert, Steven",
booktitle = "Proceedings of the 31st International Conference on Computational Linguistics",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.coling-main.154/",
pages = "2246--2260",
abstract = "Multiple choice questions (MCQs) are often used in both employee selection and training, providing objectivity, efficiency, and scalability. However, their creation is resource-intensive, requiring significant expertise and financial investment. This study leverages large language models (LLMs) and prompt engineering techniques to automate the generation and validation of MCQs, particularly within the context of university regulations. Mainly, two novel approaches are proposed in this work: an automatic question generation system for university resolution and an automatic evaluation system to assess the performance of MCQ generation systems. The generation system combines different prompt engineering techniques and a review process to create well formulated questions. The evaluation system uses prompt engineering combined with an advanced LLM model to assess the integrity of the generated question. Experimental results demonstrate the effectiveness of both systems. The findings highlight the transformative potential of LLMs in educational assessment, reducing the burden on human resources and enabling scalable, cost-effective MCQ generation."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mucciaccia-etal-2025-automatic">
<titleInfo>
<title>Automatic Multiple-Choice Question Generation and Evaluation Systems Based on LLM: A Study Case With University Resolutions</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sérgio</namePart>
<namePart type="given">Silva</namePart>
<namePart type="family">Mucciaccia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thiago</namePart>
<namePart type="family">Meireles Paixão</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Filipe</namePart>
<namePart type="family">Wall Mutz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Claudine</namePart>
<namePart type="family">Santos Badue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alberto</namePart>
<namePart type="family">Ferreira de Souza</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thiago</namePart>
<namePart type="family">Oliveira-Santos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 31st International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Owen</namePart>
<namePart type="family">Rambow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marianna</namePart>
<namePart type="family">Apidianaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="given">Di</namePart>
<namePart type="family">Eugenio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Schockaert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Multiple choice questions (MCQs) are often used in both employee selection and training, providing objectivity, efficiency, and scalability. However, their creation is resource-intensive, requiring significant expertise and financial investment. This study leverages large language models (LLMs) and prompt engineering techniques to automate the generation and validation of MCQs, particularly within the context of university regulations. Mainly, two novel approaches are proposed in this work: an automatic question generation system for university resolution and an automatic evaluation system to assess the performance of MCQ generation systems. The generation system combines different prompt engineering techniques and a review process to create well formulated questions. The evaluation system uses prompt engineering combined with an advanced LLM model to assess the integrity of the generated question. Experimental results demonstrate the effectiveness of both systems. The findings highlight the transformative potential of LLMs in educational assessment, reducing the burden on human resources and enabling scalable, cost-effective MCQ generation.</abstract>
<identifier type="citekey">mucciaccia-etal-2025-automatic</identifier>
<location>
<url>https://aclanthology.org/2025.coling-main.154/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>2246</start>
<end>2260</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Automatic Multiple-Choice Question Generation and Evaluation Systems Based on LLM: A Study Case With University Resolutions
%A Mucciaccia, Sérgio Silva
%A Meireles Paixão, Thiago
%A Wall Mutz, Filipe
%A Santos Badue, Claudine
%A Ferreira de Souza, Alberto
%A Oliveira-Santos, Thiago
%Y Rambow, Owen
%Y Wanner, Leo
%Y Apidianaki, Marianna
%Y Al-Khalifa, Hend
%Y Eugenio, Barbara Di
%Y Schockaert, Steven
%S Proceedings of the 31st International Conference on Computational Linguistics
%D 2025
%8 January
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F mucciaccia-etal-2025-automatic
%X Multiple choice questions (MCQs) are often used in both employee selection and training, providing objectivity, efficiency, and scalability. However, their creation is resource-intensive, requiring significant expertise and financial investment. This study leverages large language models (LLMs) and prompt engineering techniques to automate the generation and validation of MCQs, particularly within the context of university regulations. Mainly, two novel approaches are proposed in this work: an automatic question generation system for university resolution and an automatic evaluation system to assess the performance of MCQ generation systems. The generation system combines different prompt engineering techniques and a review process to create well formulated questions. The evaluation system uses prompt engineering combined with an advanced LLM model to assess the integrity of the generated question. Experimental results demonstrate the effectiveness of both systems. The findings highlight the transformative potential of LLMs in educational assessment, reducing the burden on human resources and enabling scalable, cost-effective MCQ generation.
%U https://aclanthology.org/2025.coling-main.154/
%P 2246-2260
Markdown (Informal)
[Automatic Multiple-Choice Question Generation and Evaluation Systems Based on LLM: A Study Case With University Resolutions](https://aclanthology.org/2025.coling-main.154/) (Mucciaccia et al., COLING 2025)
ACL