Do Conversational Interfaces Limit Creativity? Exploring Visual Graph Systems for Creative Writing

2025-07-10

AI Summary

Linear, sequential chat interfaces constrain nonlinear exploration and cognitive visualization in creative writing. To address this, we propose a node-graph–based visual interaction system that encapsulates generative AI models as draggable, reusable cognitive nodes, enabling users to dynamically construct, reconfigure, and backtrack through compositional workflows—thereby transcending the rigidity of predefined LLM chains. Grounded in creative cognition theory, the system integrates principled visualization design with modular, template-driven components to enhance ideational flexibility and process controllability. A small-scale user study demonstrates that, compared to conventional chat interfaces, our system significantly improves idea divergence, traceability of thought pathways, and writing progression efficiency. These findings establish a novel, nonlinear human-AI collaboration paradigm for AI-augmented creativity.

Technology Category

• Cognitive Modeling & Cognitive Systems: Computational Creativity
• Humans and AI: Intelligent User Interfaces
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

We present a graphical, node-based system through which users can visually chain generative AI models for creative tasks. Research in the area of chaining LLMs has found that while chaining provides transparency, controllability and guardrails to approach certain tasks, chaining with pre-defined LLM steps prevents free exploration. Using cognitive processes from creativity research as a basis, we create a system that addresses the inherent constraints of chat-based AI interactions. Specifically, our system aims to overcome the limiting linear structure that inhibits creative exploration and ideation. Further, our node-based approach enables the creation of reusable, shareable templates that can address different creative tasks. In a small-scale user study, we find that our graph-based system supports ideation and allows some users to better visualise and think through their writing process when compared to a similar conversational interface. We further discuss the weaknesses and limitations of our system, noting the benefits to creativity that user interfaces with higher complexity can provide for users who can effectively use them.

Problem

• Overcoming linear chat-based AI constraints for creativity
• Enabling reusable visual templates for creative tasks
• Supporting ideation and writing process visualization

Innovation

• Visual node-based system for AI model chaining
• Overcomes linear chat-based AI constraints
• Enables reusable shareable creative templates