Litcius/Paper detail

Systematic synthesis of design prompts for large language models in conceptual design

裕哉 川田, Ang Liu, Yun Dai, Keisuke Nagato, Masayuki Nakao

2024CIRP Annals32 citationsDOIOpen Access PDF

Abstract

Recent advancements in large language models (LLMs) demonstrate great potential in supporting engineering design, especially conceptual design. Prompt engineering plays an important role in facilitating designer-LLM collaboration in conceptual design. This paper proposes a new classification scheme that categorizes design-specific prompts into multiple classes. It also introduces different patterns for synthesizing design prompts, being grounded in the theoretical foundations of prompt engineering and domain-specific design methodology. A design experiment, utilizing ChatGPT, was conducted to investigate the impacts of different syntheses of design prompts on the effectiveness of LLM in concept generation, as measured by the metrics of novelty and diversity.

Topics & Concepts

NoveltyConceptual designDesign languageComputer scienceEngineering design processDomain (mathematical analysis)Diversity (politics)Software engineeringSystems engineeringEngineeringHuman–computer interactionProgramming languagePsychologyMathematical analysisSocial psychologyAnthropologySociologyMechanical engineeringMathematicsDesign Education and PracticeTopic ModelingNatural Language Processing Techniques
Systematic synthesis of design prompts for large language models in conceptual design | Litcius