@inproceedings{4b005d741ca142e09870fd7a9bf221f7,
title = "EduBench: A Comprehensive Benchmarking Dataset for Evaluating Large Language Models in Diverse Educational Scenarios",
abstract = "As large language models continue to advance, their application in educational contexts remains underexplored and under-optimized. In this paper, we address this gap by introducing the first diverse benchmark tailored for educational scenarios, incorporating synthetic data containing 9 major scenarios and over 4,000 distinct educational contexts. To enable comprehensive assessment, we propose a set of multi-dimensional evaluation rubrics that cover 12 critical aspects relevant to both teachers and students. We further apply human annotation to ensure the effectiveness of the model-generated evaluation responses. Additionally, we succeed to train a relatively small-scale model on our constructed dataset and demonstrate that it can achieve performance comparable to state-of-the-art large models (e.g., Deepseek V3, Qwen Max) on the test set. Overall, this work provides a practical foundation for the development and evaluation of education-oriented language models.",
author = "Bin Xu and Yu Bai and Huashan Sun and Yiguan Lin and Siming Liu and Xinyue Liang and Yaolin Li and Zhuangzhi Dong and Jingren Zhang and Yufan Deng and Xinyu Zou and Yang Gao and Heyan Huang",
note = "Publisher Copyright: {\textcopyright} 2026 Association for Computational Linguistics.; 64th Annual Meeting of the Association for Computational Linguistics, ACL 2026 ; Conference date: 02-07-2026 Through 07-07-2026",
year = "2026",
doi = "10.18653/v1/2026.acl-long.987",
language = "English",
series = "Proceedings of the Annual Meeting of the Association for Computational Linguistics",
publisher = "Association for Computational Linguistics (ACL)",
pages = "21615--21645",
editor = "Maria Liakata and Moreira, \{Viviane P.\} and Jiajun Zhang and David Jurgens",
booktitle = "Long Papers",
address = "United States",
}