@inproceedings{yancey-etal-2023-rating,
title = "Rating Short {L}2 Essays on the {CEFR} Scale with {GPT}-4",
author = "Yancey, Kevin P. and
Laflair, Geoffrey and
Verardi, Anthony and
Burstein, Jill",
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-1.49",
doi = "10.18653/v1/2023.bea-1.49",
pages = "576--584",
abstract = "Essay scoring is a critical task used to evaluate second-language (L2) writing proficiency on high-stakes language assessments. While automated scoring approaches are mature and have been around for decades, human scoring is still considered the gold standard, despite its high costs and well-known issues such as human rater fatigue and bias. The recent introduction of large language models (LLMs) brings new opportunities for automated scoring. In this paper, we evaluate how well GPT-3.5 and GPT-4 can rate short essay responses written by L2 English learners on a high-stakes language assessment, computing inter-rater agreement with human ratings. Results show that when calibration examples are provided, GPT-4 can perform almost as well as modern Automatic Writing Evaluation (AWE) methods, but agreement with human ratings can vary depending on the test-taker{'}s first language (L1).",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yancey-etal-2023-rating">
<titleInfo>
<title>Rating Short L2 Essays on the CEFR Scale with GPT-4</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Yancey</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Geoffrey</namePart>
<namePart type="family">Laflair</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anthony</namePart>
<namePart type="family">Verardi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jill</namePart>
<namePart type="family">Burstein</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>Essay scoring is a critical task used to evaluate second-language (L2) writing proficiency on high-stakes language assessments. While automated scoring approaches are mature and have been around for decades, human scoring is still considered the gold standard, despite its high costs and well-known issues such as human rater fatigue and bias. The recent introduction of large language models (LLMs) brings new opportunities for automated scoring. In this paper, we evaluate how well GPT-3.5 and GPT-4 can rate short essay responses written by L2 English learners on a high-stakes language assessment, computing inter-rater agreement with human ratings. Results show that when calibration examples are provided, GPT-4 can perform almost as well as modern Automatic Writing Evaluation (AWE) methods, but agreement with human ratings can vary depending on the test-taker’s first language (L1).</abstract>
<identifier type="citekey">yancey-etal-2023-rating</identifier>
<identifier type="doi">10.18653/v1/2023.bea-1.49</identifier>
<location>
<url>https://aclanthology.org/2023.bea-1.49</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>576</start>
<end>584</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Rating Short L2 Essays on the CEFR Scale with GPT-4
%A Yancey, Kevin P.
%A Laflair, Geoffrey
%A Verardi, Anthony
%A Burstein, Jill
%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 yancey-etal-2023-rating
%X Essay scoring is a critical task used to evaluate second-language (L2) writing proficiency on high-stakes language assessments. While automated scoring approaches are mature and have been around for decades, human scoring is still considered the gold standard, despite its high costs and well-known issues such as human rater fatigue and bias. The recent introduction of large language models (LLMs) brings new opportunities for automated scoring. In this paper, we evaluate how well GPT-3.5 and GPT-4 can rate short essay responses written by L2 English learners on a high-stakes language assessment, computing inter-rater agreement with human ratings. Results show that when calibration examples are provided, GPT-4 can perform almost as well as modern Automatic Writing Evaluation (AWE) methods, but agreement with human ratings can vary depending on the test-taker’s first language (L1).
%R 10.18653/v1/2023.bea-1.49
%U https://aclanthology.org/2023.bea-1.49
%U https://doi.org/10.18653/v1/2023.bea-1.49
%P 576-584
Markdown (Informal)
[Rating Short L2 Essays on the CEFR Scale with GPT-4](https://aclanthology.org/2023.bea-1.49) (Yancey et al., BEA 2023)
ACL
- Kevin P. Yancey, Geoffrey Laflair, Anthony Verardi, and Jill Burstein. 2023. Rating Short L2 Essays on the CEFR Scale with GPT-4. In Proceedings of the 18th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2023), pages 576–584, Toronto, Canada. Association for Computational Linguistics.