Seeing the Hivemind: A Consensus-Aware Interaction Technique for Mitigating AI Homogenization
2026-06-08 • Human-Computer Interaction
Human-Computer InteractionArtificial Intelligence
AI summaryⓘ
The authors studied how people use AI for creative work like writing and found that AI can sometimes make creativity less diverse. They proposed a new method called the Semantic Repulsion Technique (SRT) to make AI-generated content more varied. In tests, SRT increased diversity and reduced common repeated phrases, while users found its outputs more useful and clear. The authors also found that making ideas more original did not mean they were harder to understand. These results help guide creating AI tools that support creativity without making everything sound the same.
Semantic Repulsion TechniqueAI creativitysemantic diversityhuman-AI interactioncreative writingoriginalitycoherenceuser studycontent homogenization
Authors
Muhammad Haris Khan, Joel wester
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.