GenAlign: Visual knowledge graphs as interactive substrates for property-aligned generative design

초록

Designers often describe goals using ambiguous adjectives (e.g., modern); however, generative AI systems struggle to navigate this ambiguity, creating misalignment between language, intent, and outcomes. When the intended meaning remains implicit and unstructured, design generation cannot be guided precisely, resulting in semantic drift. Rather than logging past user operations, we present GenAlign, a graph-backed, human-in-the-loop design support system that externalizes cognitive visual attributes as segment-property bindings in a visual knowledge graph (VKG). GenAlign externalizes abstract attributes as segment-property bindings and maintains them as inspectable, reusable, and personalized bindings through real-time VKG updates. In a within-subject study with 24 professional designers, GenAlign transformed abstract attributes into reusable property vocabularies, supported personalized design strategies, and reduced per-step semantic drift across iterations. We discuss how VKG functions as an operational boundary object that bridges interpretive and executable design representations rather than eliminates ambiguity.

키워드