Scholarlink

Design Knowledge (DK) is the understanding of creating and improving artifacts to solve real-world problems. DK contributions often remain isolated, lacking integration and accumulation. This work explores using Large Language Models (LLMs) to build Knowledge Graphs for DK accumulation. We present Humidor, a zero-shot LLM framework that implements Wieringa’s CGAR model (Context, Goals, Artifact, Requirements) for structured DK representation. The method involves extracting CGAR expressions from manuscripts into localGraphs and merging them into a globalGraph for cumulative knowledge building.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Humidor: A Zero-Shot LLM Approach for Cumulative Knowledge Building in Design Science Research

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Oscar Díaz,
  • Xabier Garmendia,
  • Martin Horsfield

摘要

Design Knowledge (DK) is the understanding of creating and improving artifacts to solve real-world problems. DK contributions often remain isolated, lacking integration and accumulation. This work explores using Large Language Models (LLMs) to build Knowledge Graphs for DK accumulation. We present Humidor, a zero-shot LLM framework that implements Wieringa’s CGAR model (Context, Goals, Artifact, Requirements) for structured DK representation. The method involves extracting CGAR expressions from manuscripts into localGraphs and merging them into a globalGraph for cumulative knowledge building.