@inproceedings{eltanbouly-etal-2026-one,
title = "Is One Dataset Enough for Evaluation? Studying Generalizability of Automated Essay Scoring Models",
author = "Eltanbouly, Sohaila and
Sayed, Marwan and
Elsayed, Tamer",
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.29/",
doi = "10.63317/4sepdcv3iix7",
pages = "431--440",
abstract = "Automated Essay Scoring (AES) has made significant advancements in writing assessment. Recently, cross-prompt AES has gained attention because of its focus on generalizing to unseen prompts. Despite the promise of these advancements, a critical question remains: how generalizable and robust are those models when applied to diverse datasets? This study assesses the generalizability of eight cross-prompt AES models across three different datasets. We employ two experimental setups: the within-dataset approach, where both training and testing occur on the same dataset, and the cross-dataset approach, which challenges the models by evaluating their performance on previously unseen datasets. The experimental results show significant performance inconsistencies, highlighting that relying on a single dataset is insufficient for building robust and generalizable AES systems."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="eltanbouly-etal-2026-one">
<titleInfo>
<title>Is One Dataset Enough for Evaluation? Studying Generalizability of Automated Essay Scoring Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sohaila</namePart>
<namePart type="family">Eltanbouly</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marwan</namePart>
<namePart type="family">Sayed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tamer</namePart>
<namePart type="family">Elsayed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Automated Essay Scoring (AES) has made significant advancements in writing assessment. Recently, cross-prompt AES has gained attention because of its focus on generalizing to unseen prompts. Despite the promise of these advancements, a critical question remains: how generalizable and robust are those models when applied to diverse datasets? This study assesses the generalizability of eight cross-prompt AES models across three different datasets. We employ two experimental setups: the within-dataset approach, where both training and testing occur on the same dataset, and the cross-dataset approach, which challenges the models by evaluating their performance on previously unseen datasets. The experimental results show significant performance inconsistencies, highlighting that relying on a single dataset is insufficient for building robust and generalizable AES systems.</abstract>
<identifier type="citekey">eltanbouly-etal-2026-one</identifier>
<identifier type="doi">10.63317/4sepdcv3iix7</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.29/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>431</start>
<end>440</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Is One Dataset Enough for Evaluation? Studying Generalizability of Automated Essay Scoring Models
%A Eltanbouly, Sohaila
%A Sayed, Marwan
%A Elsayed, Tamer
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F eltanbouly-etal-2026-one
%X Automated Essay Scoring (AES) has made significant advancements in writing assessment. Recently, cross-prompt AES has gained attention because of its focus on generalizing to unseen prompts. Despite the promise of these advancements, a critical question remains: how generalizable and robust are those models when applied to diverse datasets? This study assesses the generalizability of eight cross-prompt AES models across three different datasets. We employ two experimental setups: the within-dataset approach, where both training and testing occur on the same dataset, and the cross-dataset approach, which challenges the models by evaluating their performance on previously unseen datasets. The experimental results show significant performance inconsistencies, highlighting that relying on a single dataset is insufficient for building robust and generalizable AES systems.
%R 10.63317/4sepdcv3iix7
%U https://aclanthology.org/2026.lrec-1.29/
%U https://doi.org/10.63317/4sepdcv3iix7
%P 431-440
Markdown (Informal)
[Is One Dataset Enough for Evaluation? Studying Generalizability of Automated Essay Scoring Models](https://aclanthology.org/2026.lrec-1.29/) (Eltanbouly et al., LREC 2026)
ACL