What question did this study set out to answer?

The study aims to explore the differences in creativity between humans and Large Language Models (LLMs) across various writing tasks.

February 8, 2026Open Access

Human vs. LLM Creativity: A Comparative Analysis of Task-Dependent Asymmetry and Linguistic Mechanisms

Key Points

The study aims to explore the differences in creativity between humans and Large Language Models (LLMs) across various writing tasks.
Two-stage experimental design comparing Human-Only, LLM-Only, and LLM-Assisted writing performances.
Focus on propositional and creative writing tasks.
Analysis using Hierarchical Moderated Regression to investigate linguistic pathways.
Human authors demonstrated greater originality in high-demand creative tasks.
LLMs outperformed in execution quality across diverse tasks.
Identified four exploratory writing creativity profiles: Ideal, Safe, Moderate, and Plain.
A 'Collaboration Trap' was observed, where suboptimal LLMs did not enhance human performance.

Abstract

This study investigates the distinct mechanisms of human versus Large Language Model (LLM) creativity. Employing a two-stage experimental design, we systematically compared Human-Only, LLM-Only, and LLM-Assisted performance across propositional and creative writing tasks. Results revealed a critical asymmetry contingent upon the research context: human authors exhibited higher originality in high-demand creative tasks, whereas LLMs governed execution quality, maintaining superior effectiveness across different tasks and cohorts. This pattern is characterized by four exploratory writing creativity profiles: Ideal, Safe, Moderate, and Plain. The distribution of human and LLM writings across these profiles was strikingly different. Hierarchical Moderated Regression analysis uncovered divergent linguistic pathways: human originality is predicted by markers of subjective cognitive investment, while LLM effectiveness is mechanistically driven by optimized structural coherence. Furthermore, the study identified a “Collaboration Trap” during collaboration with a suboptimal LLM. This partnership failed to improve human performance relative to LLM-Only benchmarks and induced cognitive anchoring, leading humans to mimic AI complexity without quality gains. These insights offer critical implications for preserving human agency and avoiding homogenization in future human–AI collaborative writing pedagogies.

Bookmark

View Full Paper