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

TL;DR

This study compares human and AI creativity in writing tasks, finding that humans excel in originality while AI maintains effectiveness through structural coherence.

Contribution

The study introduces a framework for understanding task-dependent asymmetry and linguistic mechanisms in human versus LLM creativity.

Findings

Humans show higher originality in high-demand creative tasks, while LLMs maintain superior effectiveness across tasks.

Four writing creativity profiles (Ideal, Safe, Moderate, Plain) show distinct distributions between human and LLM outputs.

Collaboration with suboptimal LLMs can reduce human performance and induce cognitive anchoring.

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.

Figures