Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| 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 |