Towards Defining, Measuring, and Leveraging Creativity in AI Applications
Despite extensive research, computational creativity still lacks a conceptually grounded, practically relevant, and empirically applicable formal definition across contexts such as art, scientific research, and games.
This research paper addresses the challenge of defining and measuring creativity in AI applications, proposing a formal mathematical framework grounded in psychological theories of creativity.
What happened
The paper presents a formal framework for measuring creativity in AI, validated through applications in chess move analysis and artistic evaluation. It addresses gaps in existing approaches by combining psychological theories with computational methods.
Why it matters
A standardized way to measure creativity in AI could improve applications in creative industries, scientific discovery, and game-playing systems, enabling more reliable evaluation of AI-generated outputs.
- Creativity in AI requires formal definitions grounded in interdisciplinary theories.
- Domain-specific adaptations are critical for effective creativity measurement.
- Validation through real-world applications strengthens the practical relevance of AI frameworks.
The bigger picture
The framework provides a foundation for developing AI systems that can objectively assess creativity, potentially enhancing tools for art generation, scientific research, and game strategy analysis.
The study advances computational creativity by offering a unified mathematical approach to measure creativity across diverse domains, validated through chess and art analysis.
Technical details
- Boden's three criteria: newness (originality), value (usefulness), and surprise (unexpectedness)
- Domain-specific adaptation of creativity metrics
- Mathematical formulation combining newness, value, and surprise
FAQ
What is the main contribution of this paper?
A formal mathematical definition of creativity based on psychological principles, validated in chess and art domains.
How does the framework define creativity?
Through three core criteria: newness (originality), value (usefulness), and surprise (unexpectedness), adapted to specific contexts.
What applications were used to test the framework?
Analysis of chess moves and assessment of paintings by artists like Picasso and Renoir.
This summary and analysis were generated with AI from the original article and may contain errors. Read the original for the full story.
Read the full story
Originally published by arXiv - cs.AI on Oct 12, 2026.
Comments
Sign in to join the discussion.