Seeing the Hivemind: A Consensus-Aware Interaction Technique for Mitigating AI Homogenization

2026-06-08

AI Summary

This study addresses the tendency of AI-driven creative writing to diminish individual creativity and produce homogeneous outputs. To counter this, we propose Semantic Repulsion Technique (SRT), which introduces a consensus-aware mechanism that dynamically suppresses high-frequency consensus phrases during text generation, thereby enhancing semantic diversity while preserving coherence. Combining a novel semantic repulsion algorithm with computational evaluation and user studies, we quantitatively measure gains in diversity and reductions in consensus phrase usage. Experimental results demonstrate that SRT increases semantic diversity by 85%–167% and reduces consensus phrases by 43%–95%. Users significantly preferred SRT-generated texts for their usefulness and coherence, with 68.8% expressing willingness to continue using the system, indicating that SRT effectively mitigates the homogenization commonly observed in AI-generated content.

Abstract

People are increasingly using AI for creative tasks such as writing. While adoption continues to grow, this form of use risks undermining individual creativity locally and reducing the heterogeneity of creative output at scale. In response, we introduce the Semantic Repulsion Technique (SRT) and evaluate it both computationally and through a study with 16 participants who regularly use AI for creative tasks. Our computational assessment reveals that SRT increases semantic diversity by 85--167\% while reducing consensus phrases by 43--95\% across task modes. In the user study, SRT outputs received higher usefulness ($p = .019$, $W = .208$) and coherence ratings ( $p = .006$, $W = .260$); 68.8\% of participants were willing to use SRT-Strong for multiple tasks versus 18.8\% for baselines. Originality and coherence ratings were positively correlated across all systems ($ρ= +.40$ to $+.67$), suggesting that divergence need not compromise readability. Taken together, these preliminary findings can inform the design of AI systems that aim to support everyday creativity without contributing to homogenization.

Problem

• AI homogenization
• creativity
• semantic diversity
• consensus phrases
• creative tasks

Innovation

• Semantic Repulsion Technique
• AI homogenization
• semantic diversity
• creative AI
• consensus-aware interaction