From the Studio to Academia: Design and Evaluation of a Knowledge-Augmented GenAI System to Empower Design Undergraduates' Design Research Writing
Abstract
Design undergraduates often possess strong visual intuition but struggle to translate tacit design knowledge into rigorous academic argumentation. While GenAI offers writing support, generic models frequently suffer from hallucinations and superficiality, failing to address the specific epistemic needs of design research. To bridge this gap, we introduce a domain-specific, knowledge-augmented GenAI system that utilizes Retrieval-Augmented Generation (RAG) and persona-based prompting to guide students through the research process. We conducted a quasi-experimental study in a Design Research Methods course, comprising an expert double-blind review of final papers (N = 10) and student interviews (N = 6). Results indicate that the system enhanced problem definition and analytical quality, though improvements in methodological execution were limited. Qualitative findings reveal that while students valued the system's accuracy and emotional support, their needs evolved from seeking answers to seeking scaffolding for critical thinking. This work offers empirical evidence for the HCI and educational technology communities regarding the use of GenAI in design education.
Read the paper
Related studies
- Knowledge Management Perspective of Generative Artificial Intelligence
- Navigating Generative Artificial Intelligence Promises and Perils for Knowledge and Creative Work
- Characterizing the evolving research on enterprise content management
- Large language models and multimodal foundation models for precision oncology
- From Generative AI to Extended Reality: Multidisciplinary Perspectives on the Challenges, Opportunities, and Future of Educational Computing
- Generative Artificial Intelligence: A New Engine for Advancing Environmental Science and Engineering
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.