Using large language models to evaluate alternative uses task flexibility score

Eran Hadas and Arnon Hershkovitz · Thinking Skills and Creativity, 52, Article 101549 · 2024

Summary

This paper introduces a large-language-model approach to automating the flexibility dimension of the Alternative Uses Task. The method generates semantic categories for uses and classifies responses into them, producing scores that can be compared with human judgments and used in larger-scale creativity assessment.

Topics

Alternative Uses Task · creativity · divergent thinking · flexibility · large language models · automated scoring

Citation

Hadas, E., & Hershkovitz, A. (2024). Using large language models to evaluate alternative uses task flexibility score. Thinking Skills and Creativity, 52, Article 101549. https://doi.org/10.1016/j.tsc.2024.101549

Full text

The publisher version is linked above. No local full-text file is provided here unless a rights-cleared author manuscript is available.