Rubric-guided generative AI for scalable creativity assessment in educational games
, 
Hongming Li, ,
Proceedings of the 20th International Conference of the Learning Sciences - ICLS 2026, pp. 2828–2830 · 2026
Abstract
Assessing creativity at scale remains challenging in learning sciences. This study examined whether GPT-4o could assess creativity in 421 student-designed levels from Physics Playground. Using a structured rubric, GPT-4o ratings were compared with human raters. Results showed strong correlations (r = .74) with multimodal inputs, and reliability analyses showed consistent performance across runs. Findings suggest that rubric-guided LLMs can approximate human creativity judgments efficiently. This approach offers a promising method for scalable automated creativity assessment.
Materials
Cite
Rahimi, S., Li, H., Esmaeiligoujar, S., & Ercan, D. (2026). Rubric-guided generative AI for scalable creativity assessment in educational games. In Proceedings of the 20th International Conference of the Learning Sciences - ICLS 2026 (pp. 2828–2830). International Society of the Learning Sciences. https://doi.org/10.22318/icls2026.756846
@inproceedings{rahimi2026rubricguided,
author = {Rahimi, Seyedahmad and Li, Hongming and Esmaeiligoujar, Salah and Ercan, Deniz},
title = {Rubric-guided generative AI for scalable creativity assessment in educational games},
booktitle = {Proceedings of the 20th International Conference of the Learning Sciences - ICLS 2026},
year = {2026},
pages = {2828--2830},
publisher = {International Society of the Learning Sciences},
doi = {10.22318/icls2026.756846},
url = {https://repository.isls.org/handle/1/13069}
}Zotero and Mendeley save this paper from the page in one click.