Slides2MindMap: Reconstructing Cognitively Efficient Knowledge Hierarchies from Lecture Slides

2026-08-01

AI Summary

This work proposes the Slides2MindMap task, which aims to automatically construct cognitively efficient, hierarchical knowledge structures—i.e., mind maps—from fragmented lecture slides. To facilitate research in this direction, the authors introduce S2M-Bench, a benchmark comprising 24 courses and 12,774 slide pages, along with AutoMindMap, an intelligent agent framework grounded in the Structure Building Framework. AutoMindMap employs a two-stage optimization mechanism: it first establishes a global knowledge backbone through skeleton anchoring, then refines local knowledge via context-aware summarization and decoupled local-global integration. The framework leverages vision-language models to enable automated evaluation. Experimental results demonstrate that AutoMindMap significantly outperforms existing approaches, exhibiting strong robustness across multiple models and scenarios, as well as practical utility in educational settings.

Abstract

Generating mind maps from lecture slides can help learners efficiently assimilate fragmented knowledge, promising substantial benefits for intelligent education. However, dedicated automatic generation and evaluation frameworks remain underexplored and challenging, requiring a global-local knowledge focus balance and handling large-scale, heterogeneous slides. We formulate the Slides2MindMap task, which aims to reconstruct cognitively efficient knowledge hierarchies from a course's slide deck collection. For systematic evaluation, we introduce S2M-Bench, a benchmark comprising 12,774 slide pages with expert-annotated mind maps spanning 24 university courses. S2M-Bench includes a cognitive-science-grounded evaluation framework that integrates ground-truth-based comparison, structure conformity analysis, and VLM-as-a-Judge. To address this task, we propose AutoMindMap, an agentic framework inspired by the Structure Building Framework. AutoMindMap comprises Skeleton Laying for global scaffold anchoring, Iterative Knowledge Integration augmented by context-aware summarization, and Dual-Stage Refinement with a local-global decoupling mechanism. The framework reconciles local knowledge faithfulness with global coherence, and adapts to slide-specific features. Experiments on S2M-Bench demonstrate that AutoMindMap outperforms baselines and achieves superior robustness across different models and scenarios, underscoring its pedagogical application value.

Problem

• mind map generation
• lecture slides
• knowledge hierarchy
• cognitive efficiency
• intelligent education

Innovation

• Slides2MindMap
• AutoMindMap
• S2M-Bench
• knowledge hierarchy reconstruction
• cognitive efficiency