Personalized AI Scaffolds Synergistic Multi-Turn Collaboration in Creative Work
🤖 AI Summary
Human-AI collaboration often fails to adequately support creative cognition and domain-specific expertise due to the lack of personalized cognitive scaffolding. Method: We propose a theoretical framework—“Personalization as External Cognitive Scaffolding”—grounded in psychometric profiling and work-style interviews, integrated into a large language model–driven AI assistant that dynamically adapts interaction strategies based on users’ divergent thinking tendencies, domain expertise, and real-time interview feedback. The system enhances shared memory, attentional coordination, and inferential consistency across iterative creative tasks. Contribution/Results: In empirical evaluation, our personalized assistant significantly outperformed generic AI baselines: marketing proposal quality increased by 32%, creativity scores by 28% (p < 0.01), and subjective measures—including perceived support, feedback satisfaction, and trust—showed substantial improvements (p < 0.01). This work establishes a novel paradigm for shared cognitive modeling and trustworthy human-AI co-creation.
Application Category
📝 Abstract
As AI becomes more deeply embedded in knowledge work, building assistants that support human creativity and expertise becomes more important. Yet achieving synergy in human-AI collaboration is not easy. Providing AI with detailed information about a user's demographics, psychological attributes, divergent thinking, and domain expertise may improve performance by scaffolding more effective multi-turn interactions. We implemented a personalized LLM-based assistant, informed by users' psychometric profiles and an AI-guided interview about their work style, to help users complete a marketing task for a fictional startup. We randomized 331 participants to work with AI that was either generic (n = 116), partially personalized (n = 114), or fully personalized (n=101). Participants working with personalized AI produce marketing campaigns of significantly higher quality and creativity, beyond what AI alone could have produced. Compared to generic AI, personalized AI leads to higher self-reported levels of assistance and feedback, while also increasing participant trust and confidence. Causal mediation analysis shows that personalization improves performance indirectly by enhancing collective memory, attention, and reasoning in the human-AI interaction. These findings provide a theory-driven framework in which personalization functions as external scaffolding that builds common ground and shared partner models, reducing uncertainty and enhancing joint cognition. This informs the design of future AI assistants that maximize synergy and support human creative potential while limiting negative homogenization.
Problem
Research questions and friction points this paper is trying to address.
Enhancing human-AI collaboration through personalized scaffolding in creative work
Improving marketing campaign quality and creativity via psychometric personalization
Building common ground to reduce uncertainty in multi-turn AI interactions
Innovation
Methods, ideas, or system contributions that make the work stand out.
Personalized LLM assistant using psychometric profiles
AI-guided interview to capture user work style
Personalization enhances collective memory and reasoning
🔎 Similar Papers
No similar papers found.
