From Generation to Evaluation: A Resource for Error-Categorized Question Generation from Video Transcripts

Joshua Berger, Markos Stamatakis, Anett Hoppe, Ralph Ewerth, Christian Wartena


Abstract
A key challenge in automated question generation is producing grammatically correct, error-free, and contextually relevant questions. While large language models already handle this well, smaller models that can run on consumer-grade hardware face greater difficulties. Another obstacle is the lack of large, high-quality datasets, particularly for education video transcripts, which limits the diversity and applicability of training data. On top of this, current evaluation methods either rely on strict comparison to a “ground truth,” undervaluing valid but unmatched questions, or on expert judgments, which do not scale. They do not provide insights into the nature of errors. In this paper, we introduce a dataset of real-life educational video transcripts and investigate the question-generating capabilities of small language models by assessing their output with pre-defined error categories. We also present a novel approach to automatic quality assessment by classifying questions into predefined error categories. We show that questions generated by small language models are still prone to error. Our proposed classification approach outperforms baseline approaches and matches GPT-5 performance by reaching an accuracy of 72%.
Anthology ID:
2026.lrec-1.170
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:
2166–2177
Language:
External URL:
https://lrec.elra.info/lrec2026-main-170
DOI:
10.63317/5c7pqn99wt3a
Bibkey:
Cite (ACL):
Joshua Berger, Markos Stamatakis, Anett Hoppe, Ralph Ewerth, and Christian Wartena. 2026. From Generation to Evaluation: A Resource for Error-Categorized Question Generation from Video Transcripts. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 2166–2177, Palma de Mallorca, Spain. ELRA Language Resource Association.
Cite (Informal):
From Generation to Evaluation: A Resource for Error-Categorized Question Generation from Video Transcripts (Berger et al., LREC 2026)
Copy Citation: