Scaffolding Creativity: How Divergent and Convergent LLM Personas Shape Human Machine Creative Problem-Solving

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Rosenbaum, Alon, David, Yigal, Kaufman, Eran, Ravid, Gilad, Ronen, Amit, Krebs, Assaf
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908620331941888
author Rosenbaum, Alon
David, Yigal
Kaufman, Eran
Ravid, Gilad
Ronen, Amit
Krebs, Assaf
author_facet Rosenbaum, Alon
David, Yigal
Kaufman, Eran
Ravid, Gilad
Ronen, Amit
Krebs, Assaf
contents Large language models (LLMs) are increasingly shaping creative work and problem-solving; however, prior research suggests that they may diminish unassisted creativity. To address this tension, a coach-like LLM environment was developed that embodies divergent and convergent thinking personas as two complementary processes. Effectiveness and user behavior were assessed through a controlled experiment in which participants interacted with either persona, while a control group engaged with a standard LLM providing direct answers. Notably, users' perceptions of which persona best supported their creativity often diverged from objective performance measures. Trait-based analyses revealed that individual differences predict when people utilize divergent versus convergent personas, suggesting opportunities for adaptive sequencing. Furthermore, interaction patterns reflected the design thinking model, demonstrating how persona-guided support shapes creative problem-solving. Our findings provide design principles for creativity support systems that strike a balance between exploration and convergence through persona-based guidance and personalization. These insights advance human-AI collaboration tools that scaffold rather than overshadow human creativity.
format Preprint
id arxiv_https___arxiv_org_abs_2510_26490
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Scaffolding Creativity: How Divergent and Convergent LLM Personas Shape Human Machine Creative Problem-Solving
Rosenbaum, Alon
David, Yigal
Kaufman, Eran
Ravid, Gilad
Ronen, Amit
Krebs, Assaf
Human-Computer Interaction
Large language models (LLMs) are increasingly shaping creative work and problem-solving; however, prior research suggests that they may diminish unassisted creativity. To address this tension, a coach-like LLM environment was developed that embodies divergent and convergent thinking personas as two complementary processes. Effectiveness and user behavior were assessed through a controlled experiment in which participants interacted with either persona, while a control group engaged with a standard LLM providing direct answers. Notably, users' perceptions of which persona best supported their creativity often diverged from objective performance measures. Trait-based analyses revealed that individual differences predict when people utilize divergent versus convergent personas, suggesting opportunities for adaptive sequencing. Furthermore, interaction patterns reflected the design thinking model, demonstrating how persona-guided support shapes creative problem-solving. Our findings provide design principles for creativity support systems that strike a balance between exploration and convergence through persona-based guidance and personalization. These insights advance human-AI collaboration tools that scaffold rather than overshadow human creativity.
title Scaffolding Creativity: How Divergent and Convergent LLM Personas Shape Human Machine Creative Problem-Solving
topic Human-Computer Interaction
url https://arxiv.org/abs/2510.26490