While generative AI enables high-fidelity UI generation from text prompts, users struggle to articulate design intent and evaluate or refine results—creating gulfs of execution and evaluation. To understand the information needed for UI generation, we conducted a thematic analysis of UI prompting guidelines, identifying key design semantics and discovering that they are hierarchical and interdependent. Leveraging these findings, we developed a system that enables users to specify semantics, visualize relationships, and extract how semantics are reflected in generated UIs. By making semantics serve as an intermediate representation between human intent and AI output, our system bridges both gulfs by making requirements explicit and outcomes interpretable. A comparative user study suggests that our approach enhances users’ perceived control over intent expression and outcome interpretation, and facilitates more predictable iterative refinement. Our work demonstrates how explicit semantic representation enables systematic and explainable exploration of design possibilities in AI-driven UI design.

Inspirational search, the process of exploring designs to inform and inspire new creative work, is pivotal in mobile user interface (UI) design. However, exploring the vast space of UI references remains a challenge. Existing AI-based UI search methods often miss crucial semantics like target users or the mood of apps. Additionally, these models typically require metadata like view hierarchies, limiting their practical use. We used a multimodal large language model (MLLM) to extract and interpret semantics from mobile UI images. We identified key UI semantics through a formative study and developed a semantic-based UI search system. Through computational and human evaluations, we demonstrate that our approach significantly outperforms existing UI retrieval methods, offering UI designers a more enriched and contextually relevant search experience. We enhance the understanding of mobile UI design semantics and highlight MLLMs' potential in inspirational search, providing a rich dataset of UI semantics for future studies.

Data visualizations can sometimes misrepresent the underlying data, leading to misleading interpretations. However, existing systems fail to precisely identify which parts of a visualization contribute to misleading interpretations, leaving users uncertain about the misalignments. To address this issue, we develop a pipeline that automatically identifies the misleading parts within a visualization. Given an image file, our pipeline first detects graphical components of the visualization, converting them into structured objects. We then apply an algorithm to pinpoint misleading objects and explain how they contribute to distortions in interpretation. Our user study confirms that our pipeline accurately identifies misleading visualization designs, outperforming previous baselines. We also find that our pipeline supports participants in developing revision strategies to improve misleading visualizations.