GRAPHIC--Guidelines for Reviewing Algorithmic Practices in Human-centred Design and Interaction for Creativity

TL;DR

This paper reviews AI systems in graphic design, introduces the GRAPHIC framework to analyze human-AI collaboration, and identifies research gaps in communication, control, and creativity support.

Contribution

It presents the GRAPHIC framework for evaluating AI in graphic design, addressing the challenge of balancing scientific rigor with creative subjectivity.

Findings

Identified key dimensions for system analysis: Collaboration, Processes, Principles.

Revealed gaps in communication and control in current systems.

Highlighted the need for explainable and transformational creative AI.

Abstract

Artificial Intelligence (AI) has been increasingly applied to creative domains, leading to the development of systems that collaborate with humans in design processes. In Graphic Design, integrating computational systems into co-creative workflows presents specific challenges, as it requires balancing scientific rigour with the subjective and visual nature of design practice. Following the PRISMA methodology, we identified 872 articles, resulting in a final corpus of 71 publications describing 68 unique systems. Based on this review, we introduce GRAPHIC (Guidelines for Reviewing Algorithmic Practices in Human-centred Design and Interaction for Creativity), a framework for analysing computational systems applied to Graphic Design. Its goal is to understand how current systems support human-AI collaboration in the Graphic Design discipline. The framework comprises main dimensions, which our analysis revealed to be essential across diverse system types: (1) Collaborative Panorama, (2) Processes and Modalities, and (3) Graphic Design Principles. Its application revealed research gaps, including the need to balance initiative and control between agents, improve communication through explainable interaction models, and promote systems that support transformational creativity grounded in core design principles.