Saved in:
Bibliographic Details
Main Authors: Wang, Yixuan, Huang, Yue, Qian, Hong, Wei, Yunzhao, Ding, Yifei, Wang, Wenkai, Liu, Zhi, Huang, Zhongjing, Zhou, Aimin, Guo, Jiajun
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.18398
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915957655470080
author Wang, Yixuan
Huang, Yue
Qian, Hong
Wei, Yunzhao
Ding, Yifei
Wang, Wenkai
Liu, Zhi
Huang, Zhongjing
Zhou, Aimin
Guo, Jiajun
author_facet Wang, Yixuan
Huang, Yue
Qian, Hong
Wei, Yunzhao
Ding, Yifei
Wang, Wenkai
Liu, Zhi
Huang, Zhongjing
Zhou, Aimin
Guo, Jiajun
contents Creativity has become a core competence in the era of LLMs and human-AI collaboration, underpinning innovation in real-world problem solving. Crucially, the systematic improvement of creativity necessitates scientifically valid assessment instruments. Psychometric research recognizes context-based assessment as an effective way to measure creative thinking. However, high-quality expert-designed contexts remain scarce. Existing LLM-based generators often struggle with insufficient assessment cues, weak narrative coherence, limited stylistic diversity, and poor support for creative thinking. To address these challenges, we propose AlphaContext, an evolutionary tree-based psychometric context generator for creativity assessment. First, the HyperTree Outline Planner formalizes expert-designed outlining as a rule-guided hypertree and performs top-down hierarchical planning. The MCTS-based Context Generator fills the outline via MCTS to balance global structure and local quality. Then, the Evolutionary Context Optimizer evolves contexts with MAP-Elites by repeatedly updating niche elites to jointly improve diversity and quality. Finally, the Assessment-Guided Evolution Refiner simulates virtual participants with diverse styles and recycles weak contexts for further evolution. Experiments show that AlphaContext yields an average improvement of 8% over competitive methods across 6 quality metrics.
format Preprint
id arxiv_https___arxiv_org_abs_2604_18398
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle AlphaContext: An Evolutionary Tree-based Psychometric Context Generator for Creativity Assessment
Wang, Yixuan
Huang, Yue
Qian, Hong
Wei, Yunzhao
Ding, Yifei
Wang, Wenkai
Liu, Zhi
Huang, Zhongjing
Zhou, Aimin
Guo, Jiajun
Computation and Language
Artificial Intelligence
Creativity has become a core competence in the era of LLMs and human-AI collaboration, underpinning innovation in real-world problem solving. Crucially, the systematic improvement of creativity necessitates scientifically valid assessment instruments. Psychometric research recognizes context-based assessment as an effective way to measure creative thinking. However, high-quality expert-designed contexts remain scarce. Existing LLM-based generators often struggle with insufficient assessment cues, weak narrative coherence, limited stylistic diversity, and poor support for creative thinking. To address these challenges, we propose AlphaContext, an evolutionary tree-based psychometric context generator for creativity assessment. First, the HyperTree Outline Planner formalizes expert-designed outlining as a rule-guided hypertree and performs top-down hierarchical planning. The MCTS-based Context Generator fills the outline via MCTS to balance global structure and local quality. Then, the Evolutionary Context Optimizer evolves contexts with MAP-Elites by repeatedly updating niche elites to jointly improve diversity and quality. Finally, the Assessment-Guided Evolution Refiner simulates virtual participants with diverse styles and recycles weak contexts for further evolution. Experiments show that AlphaContext yields an average improvement of 8% over competitive methods across 6 quality metrics.
title AlphaContext: An Evolutionary Tree-based Psychometric Context Generator for Creativity Assessment
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2604.18398