"A Great Start, But...": Evaluating LLM-Generated Mind Maps for Information Mapping in Video-Based Design

TL;DR

This study evaluates the effectiveness of prompt-tuned Large Language Models in generating mind maps from ethnographic videos for Video-Based Design, highlighting their strengths and limitations in capturing concepts and organizing information.

Contribution

It introduces a novel application of LLMs for automated mind map generation in VBD and compares their outputs with professional designers' work.

Findings

LLMs effectively identify central concepts.

Struggle with hierarchical organization and contextual grounding.

Highlights need for trust and workflow integration.

Abstract

Extracting concepts and understanding relationships from videos is essential in Video-Based Design (VBD), where videos serve as a primary medium for exploration but require significant effort in managing meta-information. Mind maps, with their ability to visually organize complex data, offer a promising approach for structuring and analysing video content. Recent advancements in Large Language Models (LLMs) provide new opportunities for meta-information processing and visual understanding in VBD, yet their application remains underexplored. This study recruited 28 VBD practitioners to investigate the use of prompt-tuned LLMs for generating mind maps from ethnographic videos. Comparing LLM-generated mind maps with those created by professional designers, we evaluated rated scores, design effectiveness, and user experience across two contexts. Findings reveal that LLMs effectively capture central concepts but struggle with hierarchical organization and contextual grounding. We discuss trust, customization, and workflow integration as key factors to guide future research on LLM-supported information mapping in VBD.