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

2026-04-20

AI Summary

Current approaches to generating creativity assessment scenarios with large language models often suffer from insufficient contextual cues, weak narrative coherence, limited stylistic diversity, and inadequate support for creative thinking. To address these limitations, this work proposes a novel four-stage generation framework grounded in evolutionary tree principles. The framework integrates hyper-tree outline planning, Monte Carlo Tree Search (MCTS) for content filling, MAP-Elites-based evolutionary optimization, and evaluation-guided refinement to collaboratively produce high-quality, diverse scenarios. Innovatively combining hyper-tree structures, MCTS, and MAP-Elites algorithms, the method further incorporates simulated virtual participants and a weak-scenario recycling mechanism. Empirical results demonstrate that the proposed approach outperforms existing methods by an average of 8% across six quality metrics, significantly enhancing assessment validity, narrative coherence, and stylistic variety.

Technology Category

• Cognitive Modeling & Cognitive Systems: Computational Creativity
• Humans and AI: Game Design — Procedural Content Generation & Storytelling
• Natural Language Processing: Generation

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Web Mining and Content Analysis: Web data generation and simulation
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

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.

Problem

• creativity assessment
• context generation
• psychometric context
• narrative coherence
• stylistic diversity

Innovation

• evolutionary tree
• psychometric context generation
• MCTS
• MAP-Elites
• creativity assessment