@inproceedings{degraeuwe-moerman-2026-shanel,
title = "{S}h{A}n{EL}-2: A Multilingual Benchmarking Dataset for Short-Answer Language Learning Exercises",
author = "Degraeuwe, Jasper and
Moerman, Thomas",
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-1.538/",
doi = "10.63317/3cvfqh22muoo",
pages = "6764--6771",
abstract = "Before using GenAI models as EdTech tools, their pedagogical suitability should be corroborated. In this paper, we present ShAnEL-2, a novel multilingual dataset comprising 1,185 student responses to short-answer language learning exercises corrected by teachers. We use ShAnEL-2 to establish an initial benchmark of (1) ``off-the-shelf'' GenAI models and (2) retrieval-augmented generation (RAG) techniques for the automated correction of this exercise type. With an overall accuracy of 90{\%} and recall of 95{\%}, few-shot RAG (which adds previously corrected responses to the prompt) outperforms the off-the-shelf baseline and textbook RAG setup (which adds coursebook materials) by up to 7 (accuracy) and 5 (recall) percentage points. These results confirm that LLMs learn better from examples than from analysing context and highlight GenAI{'}s particular potential as a correction assistant for teachers."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="degraeuwe-moerman-2026-shanel">
<titleInfo>
<title>ShAnEL-2: A Multilingual Benchmarking Dataset for Short-Answer Language Learning Exercises</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jasper</namePart>
<namePart type="family">Degraeuwe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thomas</namePart>
<namePart type="family">Moerman</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>Before using GenAI models as EdTech tools, their pedagogical suitability should be corroborated. In this paper, we present ShAnEL-2, a novel multilingual dataset comprising 1,185 student responses to short-answer language learning exercises corrected by teachers. We use ShAnEL-2 to establish an initial benchmark of (1) “off-the-shelf” GenAI models and (2) retrieval-augmented generation (RAG) techniques for the automated correction of this exercise type. With an overall accuracy of 90% and recall of 95%, few-shot RAG (which adds previously corrected responses to the prompt) outperforms the off-the-shelf baseline and textbook RAG setup (which adds coursebook materials) by up to 7 (accuracy) and 5 (recall) percentage points. These results confirm that LLMs learn better from examples than from analysing context and highlight GenAI’s particular potential as a correction assistant for teachers.</abstract>
<identifier type="citekey">degraeuwe-moerman-2026-shanel</identifier>
<identifier type="doi">10.63317/3cvfqh22muoo</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.538/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>6764</start>
<end>6771</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ShAnEL-2: A Multilingual Benchmarking Dataset for Short-Answer Language Learning Exercises
%A Degraeuwe, Jasper
%A Moerman, Thomas
%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 degraeuwe-moerman-2026-shanel
%X Before using GenAI models as EdTech tools, their pedagogical suitability should be corroborated. In this paper, we present ShAnEL-2, a novel multilingual dataset comprising 1,185 student responses to short-answer language learning exercises corrected by teachers. We use ShAnEL-2 to establish an initial benchmark of (1) “off-the-shelf” GenAI models and (2) retrieval-augmented generation (RAG) techniques for the automated correction of this exercise type. With an overall accuracy of 90% and recall of 95%, few-shot RAG (which adds previously corrected responses to the prompt) outperforms the off-the-shelf baseline and textbook RAG setup (which adds coursebook materials) by up to 7 (accuracy) and 5 (recall) percentage points. These results confirm that LLMs learn better from examples than from analysing context and highlight GenAI’s particular potential as a correction assistant for teachers.
%R 10.63317/3cvfqh22muoo
%U https://aclanthology.org/2026.lrec-1.538/
%U https://doi.org/10.63317/3cvfqh22muoo
%P 6764-6771
Markdown (Informal)
[ShAnEL-2: A Multilingual Benchmarking Dataset for Short-Answer Language Learning Exercises](https://aclanthology.org/2026.lrec-1.538/) (Degraeuwe & Moerman, LREC 2026)
ACL