New Framework Models Interpretive Perspectives in Computational Creativity

Prerna Luthra· August 3, 2026 View original

Key takeaways

  • Creativity evaluation is subjective and depends heavily on interpretive perspectives, not just objective artifact properties.
  • Modeling different evaluative personas reveals systematic divergences in how AI-generated art is perceived.
  • Distinct visual features become salient depending on the interpretive perspective applied.
  • Incorporating multiple perspectives can enhance co-creative AI systems and human-AI collaboration.

Who benefits

Creative ArtsEntertainmentAdvertisingDesignAI Development

Summary

This paper proposes a computational approach to model how different interpretive perspectives influence the evaluation of creativity in AI-generated art, moving beyond objective assessments. It uses a twelve-trait framework across four domains and three evaluative personas to analyze artwork.

Traditional methods for evaluating computational creativity often treat "creativity" as an objective, measurable property of an artifact. However, artistic meaning is inherently subjective and varies based on individual perspectives and critical traditions. This new research introduces a computational framework designed to model these diverse interpretive perspectives, rather than seeking a single, universal measure of creativity. The study employs a twelve-trait creativity framework, organized into four conceptual domains, and operationalizes it through three distinct evaluative personas: formalist, social-historical, and iconographic. By analyzing over a thousand artworks with nearly 40,000 persona-based evaluations, the research demonstrates significant divergence in creativity assessments across these perspectives. Linear probing of image embeddings further reveals that different perspectives activate distinct visual features, confirming that creativity evaluation is deeply relational and context-dependent.

Why it matters

For professionals developing AI systems in creative fields, understanding and incorporating multiple interpretive perspectives can lead to more nuanced, human-centric, and commercially viable creative AI tools.

How to implement this in your domain

  1. 1Integrate multi-persona evaluation modules into AI art generation or design tools to assess outputs from diverse viewpoints.
  2. 2Develop user interfaces that allow human collaborators to select or define their interpretive persona when evaluating AI-generated content.
  3. 3Train creative AI models with datasets annotated by multiple evaluative perspectives to foster more versatile and context-aware outputs.
  4. 4Explore how different visual features are weighted by various interpretive personas to guide feature engineering in creative AI.

Original post by Prerna Luthra

"arXiv:2607.28644v1 Announce Type: cross Abstract: Creativity in computational systems is often evaluated as an objective property of artifacts, with existing Computational Creativity (CC) frameworks assessing creative merit at the level of outputs or systems rather than interpret…"

View on X

Originally posted by Prerna Luthra on X · view source

Want to go deeper?

Turn these trends into skills with Learnijoy's hands-on AI & tech courses.

Explore courses