AlphaContext: An Evolutionary Tree-based Psychometric Context Generator for Creativity Assessment

TL;DR

AlphaContext is an innovative evolutionary framework that generates high-quality, diverse contexts for creativity assessment, addressing limitations of existing LLM-based generators.

Contribution

It introduces a novel hierarchical, rule-guided, and evolutionary approach combining hypertree planning, MCTS, and MAP-Elites for context generation.

Findings

AlphaContext improves context quality by 8% on average across six metrics.

The method enhances diversity and coherence in generated contexts.

Experiments demonstrate superior performance over existing approaches.

Abstract

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.