ShAnEL-2: A Multilingual Benchmarking Dataset for Short-Answer Language Learning Exercises

Jasper Degraeuwe, Thomas Moerman


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.
Anthology ID:
2026.lrec-1.538
Volume:
Proceedings of the Fifteenth Language Resources and Evaluation Conference
Month:
May
Year:
2026
Address:
Palma de Mallorca, Spain
Editors:
Stelios Piperidis, Núria Bel, Henk van den Heuvel, Nancy Ide, Simon Krek, Antonio Toral
Venue:
LREC
SIG:
Publisher:
ELRA Language Resource Association
Note:
Pages:
6764–6771
Language:
External URL:
https://lrec.elra.info/lrec2026-main-538
DOI:
10.63317/3cvfqh22muoo
Bibkey:
Cite (ACL):
Jasper Degraeuwe and Thomas Moerman. 2026. ShAnEL-2: A Multilingual Benchmarking Dataset for Short-Answer Language Learning Exercises. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 6764–6771, Palma de Mallorca, Spain. ELRA Language Resource Association.
Cite (Informal):
ShAnEL-2: A Multilingual Benchmarking Dataset for Short-Answer Language Learning Exercises (Degraeuwe & Moerman, LREC 2026)
Copy Citation: