Validating AI-Based Scoring of Divergent Thinking in Elementary School Children
Summary
This conference paper validates LLM-based scoring of Alternative Uses Test responses from third- and fourth-grade students. It focuses on flexibility and originality, comparing automated scores with human ratings and established benchmarks.
Topics
Divergent thinking · elementary education · Alternative Uses Test · flexibility · originality · large language models · automated scoring
Citation
Hadas, E., Avital-Lev, B., & Hershkovitz, A. (2025). Validating AI-based scoring of divergent thinking in elementary school children. In Proceedings of the 1st International Conference on Learning Evidence and Analytics. Asia-Pacific Society for Computers in Education.