What question did this study set out to answer?

This research aims to determine if a large language model can reliably evaluate human creativity in constrained tasks typical of creative industries.

May 16, 2026TechnovationOpen Access

Evaluating creative work with artificial intelligence: Evidence from constrained innovation tasks

View Full Paper

Ask AI

Bookmark

This research aims to determine if a large language model can reliably evaluate human creativity in constrained tasks typical of creative industries.
Conducted a controlled experiment using expert-generated creative outputs.
Employed a large language model as an evaluator and compared its judgments with expert assessments.
Analyzed results based on internal consistency, evaluative variability, and task-specific dimensions.
AI evaluations demonstrated high inter-rater reliability consistent with expert judgments.
AI outputs showed lower variability and systematically higher scores compared to human judges.
AI evaluations were structured along key creative dimensions: fluency, flexibility, originality, and elaboration.

No takes yet. Share an insight, caveat, or question.

Randomized trial evaluates AI's effectiveness in assessing human creativity, suggesting it can match expert judges.

Addis et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark