Exploring the Potential of Large Language Models in Artistic Creation: Collaboration and Reflection on Creative Programming

2024-02-15

arXiv.org

AI Summary

This study addresses the lack of empirical research on reflective practices in human–LLM collaborative creative programming. Employing a controlled experiment integrating quantitative performance metrics with in-depth qualitative interviews, we compare two collaboration paradigms—“full-program invocation” versus “multi-subtask decomposition”—and, for the first time, analyze LLM-mediated artistic co-creation through the lens of reflection typology. Results demonstrate that these paradigms robustly elicit distinct reflective patterns (e.g., process-oriented vs. intention-oriented reflection), and reflection type significantly predicts programming performance, user satisfaction, and flow experience. Based on these findings, we propose empirically grounded design principles for AI collaboration in creative tasks, advancing both theoretical understanding and practical implementation of AI-augmented artistic practice.

Technology Category

• Cognitive Modeling & Cognitive Systems: Computational Creativity
• Humans and AI: Human-AI Collaboration / Human-AI Teaming
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

Recently, the potential of large language models (LLMs) has been widely used in assisting programming. However, current research does not explore the artist potential of LLMs in creative coding within artist and AI collaboration. Our work probes the reflection type of artists in the creation process with such collaboration. We compare two common collaboration approaches: invoking the entire program and multiple subtasks. Our findings exhibit artists' different stimulated reflections in two different methods. Our finding also shows the correlation of reflection type with user performance, user satisfaction, and subjective experience in two collaborations through conducting two methods, including experimental data and qualitative interviews. In this sense, our work reveals the artistic potential of LLM in creative coding. Meanwhile, we provide a critical lens of human-AI collaboration from the artists' perspective and expound design suggestions for future work of AI-assisted creative tasks.

Problem

• Investigates reflection in human-LLM co-creation for creative coding
• Compares two prompting strategies' effects on reflective behavior
• Identifies reflection types and their impact on creative engagement

Innovation

• Investigates reflection in human-LLM co-creation
• Compares entire task vs. decomposed subtask prompting
• T2 promotes frequent, strategic, generative reflection