Introducing multiplex semantic networks as multifaceted representations of creative associative knowledge across multilingual samples

2026-06-08 · Source: Takara TLDR - Daily AI Papers · Field: Science & Research — Social Sciences & Behavioral Studies, Artificial Intelligence & Machine Learning, Data Science & Analytics · Depth: Advanced, medium

Summary

This study introduces multiplex semantic networks as a comprehensive approach to modeling the associative knowledge underpinning creativity, addressing the limitations of single-task measurements. Researchers collected data from N=518 individuals across Austria, USA, Singapore, and Italy, utilizing responses from six cognitive tasks including verbal fluency and narrative writing. These responses formed semantic networks, assembled into a multiplex structure, with AI persona-based responses serving as a comparison baseline. Structural reducibility analyses revealed that distinct task layers captured non-redundant information about semantic organization. Networks from high- and low-creative human groups remained structurally distinct, contrasting with AI-generated networks which showed near-identical structures. A machine learning model, employing ridge regression with 12 features, predicted individual creativity scores, achieving a 50% improvement in proof-of-concept prediction accuracy by combining structurally similar layers. The study highlights structural measures and spreading activation dynamics as key predictive features.

Key takeaway

For AI and Research Scientists investigating cognitive abilities, this work demonstrates that multiplex semantic networks provide a superior, multifaceted representation of creative associative knowledge. You should consider integrating diverse cognitive task data into your models to capture non-redundant information, especially when distinguishing human creativity from AI-generated responses. The released dataset and code offer a valuable resource for developing more nuanced computational approaches to creativity.

Key insights

Multiplex semantic networks offer a richer, cross-cultural model for creativity by integrating diverse cognitive task data.

Principles

• Creativity relies on complex knowledge organization.
• Multiple cognitive tasks capture distinct semantic information.
• AI-generated networks lack human creativity distinctions.

Method

Researchers constructed multiplex semantic networks from six cognitive tasks across N=518 individuals. They used structural reducibility analysis and a ridge regression model with 12 features to predict creativity scores.

In practice

• Use multiplex networks for comprehensive creativity assessment.
• Integrate structural measures for predictive modeling.
• Compare human and AI associative knowledge.

Topics

• Multiplex Networks
• Semantic Memory
• Creativity Assessment
• Cognitive Tasks
• Machine Learning
• AI Persona

Code references

• GMLR-Penn/Multiplex-Thinking

Best for: AI Scientist, Research Scientist, Data Scientist

Related on AIssential

• LLM Friendly Graphs for AI Memory — From Triples to Facts — Larger, context-rich labels and subgraph representations enhance LLM comprehension of complex facts in knowledge graphs.
• Build Meaning Before Machines: Why Semantics, Ontologies, And Knowledge Graphs Matter For Agentic AI — Agentic AI requires explicit data meaning, making semantic layers and knowledge graphs essential architectural components.
• Predicting new research directions in materials science using large language models and concept graphs — LLMs and concept graphs can predict novel materials science research directions by identifying previously uncombined concepts.
• The Context Gap — "Context graphs" are a market response to the self-inflicted wound of lost process knowledge due to decades of outsourcing.
• What Makes Knowledge Graphs AI-Ready — Knowledge Graphs for AI bridge siloed data semantics with organizational ontology for machine-readable reasoning.
• Mind-Omni: A Unified Multi-Task Framework for Brain-Vision-Language Modeling via Discrete Diffusion — Mind-Omni unifies brain-vision-language tasks via discrete diffusion and a Brain Tokenizer for multi-modal interaction.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Takara TLDR - Daily AI Papers.