Are Semantic Networks Associated with Idea Originality in Artificial Creativity? A Comparison with Human Agents

2026-02-02

AI Summary

This study investigates how generative artificial intelligence—exemplified by ChatGPT-4o—supports human creativity through semantic network structures, with a focus on the mechanisms linking such models to creative originality. By integrating standardized creativity assessments with semantic network analysis, the research presents the first empirical comparison of semantic organization patterns and originality performance between large language models and human participants classified as high or low in creativity. The findings reveal that ChatGPT-4o exhibits a semantic–originality relationship akin to that of highly creative individuals and significantly outperforms low-creativity humans in originality. Furthermore, the results highlight motivational processes and model hyperparameters as critical factors underlying human–AI differences in creativity, offering both theoretical grounding and practical pathways for designing large language model–based creativity support tools.

Technology Category

• Cognitive Modeling & Cognitive Systems: Computational Creativity
• Humans and AI: Other Foundations of Human Computation & AI
• Natural Language Processing: (Large) Language Models

Application Category

• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications

Abstract

The application of generative artificial intelligence in Creativity Support Tools (CSTs) presents the challenge of interfacing two black boxes: the user's mind and the machine engine. According to Artificial Cognition, this challenge involves theories, methods, and constructs developed to study human creativity. Consistently, the paper investigated the relationship between semantic networks organisation and idea originality in Large Language Models. Data was collected by administering a set of standardised tests to ChatGPT-4o and 81 psychology students, divided into higher and lower creative individuals. The expected relationship was confirmed in the comparison between ChatGPT-4o and higher creative humans. However, despite having a more rigid network, ChatGPT-4o emerged as more original than lower creative humans. We attributed this difference to human motivational processes and model hyperparameters, advancing a research agenda for the study of artificial creativity. In conclusion, we illustrate the potential of this construct for designing and evaluating CSTs.

Problem

• Semantic Networks
• Idea Originality
• Artificial Creativity
• Large Language Models
• Creativity Support Tools

Innovation

• semantic networks
• artificial creativity
• Large Language Models
• idea originality
• Creativity Support Tools