@inproceedings{laverghetta-jr-licato-2023-generating,
title = "Generating Better Items for Cognitive Assessments Using Large Language Models",
author = "Laverghetta Jr., Antonio and
Licato, John",
editor = {Kochmar, Ekaterina and
Burstein, Jill and
Horbach, Andrea and
Laarmann-Quante, Ronja and
Madnani, Nitin and
Tack, Ana{\"\i}s and
Yaneva, Victoria and
Yuan, Zheng and
Zesch, Torsten},
booktitle = "Proceedings of the 18th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2023)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.bea-1.34",
doi = "10.18653/v1/2023.bea-1.34",
pages = "414--428",
abstract = "Writing high-quality test questions (items) is critical to building educational measures but has traditionally also been a time-consuming process. One promising avenue for alleviating this is automated item generation, whereby methods from artificial intelligence (AI) are used to generate new items with minimal human intervention. Researchers have explored using large language models (LLMs) to generate new items with equivalent psychometric properties to human-written ones. But can LLMs generate items with improved psychometric properties, even when existing items have poor validity evidence? We investigate this using items from a natural language inference (NLI) dataset. We develop a novel prompting strategy based on selecting items with both the best and worst properties to use in the prompt and use GPT-3 to generate new NLI items. We find that the GPT-3 items show improved psychometric properties in many cases, whilst also possessing good content, convergent and discriminant validity evidence. Collectively, our results demonstrate the potential of employing LLMs to ease the item development process and suggest that the careful use of prompting may allow for iterative improvement of item quality.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="laverghetta-jr-licato-2023-generating">
<titleInfo>
<title>Generating Better Items for Cognitive Assessments Using Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Laverghetta Jr.</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="family">Licato</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 18th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2023)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Kochmar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jill</namePart>
<namePart type="family">Burstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrea</namePart>
<namePart type="family">Horbach</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ronja</namePart>
<namePart type="family">Laarmann-Quante</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nitin</namePart>
<namePart type="family">Madnani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anaïs</namePart>
<namePart type="family">Tack</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Victoria</namePart>
<namePart type="family">Yaneva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zheng</namePart>
<namePart type="family">Yuan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Torsten</namePart>
<namePart type="family">Zesch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Writing high-quality test questions (items) is critical to building educational measures but has traditionally also been a time-consuming process. One promising avenue for alleviating this is automated item generation, whereby methods from artificial intelligence (AI) are used to generate new items with minimal human intervention. Researchers have explored using large language models (LLMs) to generate new items with equivalent psychometric properties to human-written ones. But can LLMs generate items with improved psychometric properties, even when existing items have poor validity evidence? We investigate this using items from a natural language inference (NLI) dataset. We develop a novel prompting strategy based on selecting items with both the best and worst properties to use in the prompt and use GPT-3 to generate new NLI items. We find that the GPT-3 items show improved psychometric properties in many cases, whilst also possessing good content, convergent and discriminant validity evidence. Collectively, our results demonstrate the potential of employing LLMs to ease the item development process and suggest that the careful use of prompting may allow for iterative improvement of item quality.</abstract>
<identifier type="citekey">laverghetta-jr-licato-2023-generating</identifier>
<identifier type="doi">10.18653/v1/2023.bea-1.34</identifier>
<location>
<url>https://aclanthology.org/2023.bea-1.34</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>414</start>
<end>428</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Generating Better Items for Cognitive Assessments Using Large Language Models
%A Laverghetta Jr., Antonio
%A Licato, John
%Y Kochmar, Ekaterina
%Y Burstein, Jill
%Y Horbach, Andrea
%Y Laarmann-Quante, Ronja
%Y Madnani, Nitin
%Y Tack, Anaïs
%Y Yaneva, Victoria
%Y Yuan, Zheng
%Y Zesch, Torsten
%S Proceedings of the 18th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2023)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F laverghetta-jr-licato-2023-generating
%X Writing high-quality test questions (items) is critical to building educational measures but has traditionally also been a time-consuming process. One promising avenue for alleviating this is automated item generation, whereby methods from artificial intelligence (AI) are used to generate new items with minimal human intervention. Researchers have explored using large language models (LLMs) to generate new items with equivalent psychometric properties to human-written ones. But can LLMs generate items with improved psychometric properties, even when existing items have poor validity evidence? We investigate this using items from a natural language inference (NLI) dataset. We develop a novel prompting strategy based on selecting items with both the best and worst properties to use in the prompt and use GPT-3 to generate new NLI items. We find that the GPT-3 items show improved psychometric properties in many cases, whilst also possessing good content, convergent and discriminant validity evidence. Collectively, our results demonstrate the potential of employing LLMs to ease the item development process and suggest that the careful use of prompting may allow for iterative improvement of item quality.
%R 10.18653/v1/2023.bea-1.34
%U https://aclanthology.org/2023.bea-1.34
%U https://doi.org/10.18653/v1/2023.bea-1.34
%P 414-428
Markdown (Informal)
[Generating Better Items for Cognitive Assessments Using Large Language Models](https://aclanthology.org/2023.bea-1.34) (Laverghetta Jr. & Licato, BEA 2023)
ACL