UISGPT: Automated Mobile UI Design Smell Detection with Large Language Models

Abstract

Manual inspection and remediation of guideline violations (UI design smells) is a knowledge-intensive, time-consuming, and context-related task that requires a high level of expertise. This paper proposes UISGPT, a novel end-to-end approach for automatically detecting user interface (UI) design smells and explaining each violation of specific design guidelines in natural language. To avoid hallucinations in large language models (LLMs) and achieve interpretable results, UISGPT uses few-shot learning and least-to-most prompting strategies to formalize design guidelines. To prevent the model from exceeding the input window size and for the enhancement of the logic in responses, UISGPT divides design smell detection into the following three subtasks: design guideline formalization, UI component information extraction, and guideline validation. The experimental results show that UISGPT performs effectively in automatically detecting design violations (F1 score of 0.729). In comparison to the latest LLM methods, the design smell reports generated by UISGPT have higher contextual consistency and user ratings.