[Paper Review] Opportunities and challenges of ChatGPT for design knowledge management

Xin Hu, Yu Tian+3 more|arXiv (Cornell University)|Apr 6, 2023

E-Learning and Knowledge Management12 citations

TL;DR

The paper reviews how ChatGPT can support design knowledge management, analyzes opportunities and challenges, and validates findings with a case study showing prompt-dependent knowledge quality.

ABSTRACT

Recent advancements in Natural Language Processing have opened up new possibilities for the development of large language models like ChatGPT, which can facilitate knowledge management in the design process by providing designers with access to a vast array of relevant information. However, integrating ChatGPT into the design process also presents new challenges. In this paper, we provide a concise review of the classification and representation of design knowledge, and past efforts to support designers in acquiring knowledge. We analyze the opportunities and challenges that ChatGPT presents for knowledge management in design and propose promising future research directions. A case study is conducted to validate the advantages and drawbacks of ChatGPT, showing that designers can acquire targeted knowledge from various domains, but the quality of the acquired knowledge is highly dependent on the prompt.

Motivation & Objective

• Provide a concise review of how design knowledge is classified and represented.
• Summarize past efforts to support designers in acquiring knowledge.
• Analyze opportunities and challenges of ChatGPT for knowledge management in design.
• Propose future research directions for integrating ChatGPT into design knowledge workflows.

Proposed method

• Classify and discuss design knowledge representation and its implications for AI-assisted access.
• Review prior work on design knowledge acquisition and support tools for designers.
• Conduct a case study to validate advantages and drawbacks of using ChatGPT in design knowledge retrieval.
• Analyze how prompt design affects the quality of knowledge acquired from ChatGPT.
• Suggest promising directions for future research in design knowledge management with ChatGPT.

Experimental results

Research questions

• RQ1 How can design knowledge be classified and represented for AI-assisted retrieval?
• RQ2 What opportunities does ChatGPT offer for aiding designers in acquiring knowledge across domains?
• RQ3 What challenges arise from integrating ChatGPT into design knowledge management, and how does prompt quality affect outcomes?
• RQ4 What future research directions are warranted to improve ChatGPT-enabled knowledge management in design?

Key findings

• ChatGPT can help designers acquire targeted knowledge from various domains.
• The quality of acquired knowledge is highly dependent on the prompt.
• ChatGPT presents both advantages and drawbacks in design knowledge management.
• The study includes a case validation demonstrating practical implications of ChatGPT in design workflows.