List рдкрд░ рд╡рд╛рдкрд╕ рдЬрд╛рдПрдБ
ЁЯУДPapers

Elicitive User Interfaces: Designing How Users Shape Generative Interfaces

Kim E. et al.
2026-09

рдкрд░рд┐рдЪрдп

September 2026 HCI paper proposing that generated interfaces should also generate ways to ask users about unstated preferences. Its six-axis design space and Ditto prototype cover questions, alternatives, editable panels, and other prompts embedded in the interface, with findings from two user studies.

рд╕рд╛рд░рд╛рдВрд╢

Why This Paper Adds New Signal:

1. Elicitation as generated UI: Makes preference discovery part of the interface instead of relying only on a chat prompt
2. Concrete design space: Describes fidelity, saliency, amount, frequency, assertiveness, and placement for asking users
3. Working probe: Ditto implements 12 elicitation techniques, including in-place alternatives and editable controls
4. User evidence: Studies found that elicitation surfaced previously unformed preferences and that preferred ways of being asked were more consistent than UI choices

Tags

generative-uiuser-preferenceselicitationpersonalizationhuman-in-the-loop
рдореВрд▓ рд▓реЗрдЦ рдкрдврд╝реЗрдВ

рдорд┐рд▓рддреЗ-рдЬреБрд▓рддреЗ рд▓реЗрдЦ

ЁЯУДPapers

Automating HCI Principles: Skills for On-Demand UI Construction

Position paper proposing machine-readable skills that guide agents as they generate task-specific interfaces. Its shared Human-AI workspace connects dialogue, task decomposition, and UI state, while inspectable skill files encode usability heuristics, accessibility criteria, cognitive-load guidance, and mixed-initiative interaction principles.

generative-uihci-skillson-demand-ui
рд▓реЗрдЦрдХ Conklin N. et al. ┬╖ 2026-10
рдФрд░ рдкрдврд╝реЗрдВ
ЁЯУДPapers

AUV-Bench: Aesthetic Understanding and Generation Evaluation for User Interfaces

September 2026 benchmark connecting aesthetic scoring, diagnosis, repair, and text-to-UI generation across 1,395 executable web interfaces. It pairs diagnosis and repair on 660 controlled-degradation cases to test whether models can translate design judgments into effective interface changes.

ui-generationaesthetic-evaluationdiagnosis-and-repair
рд▓реЗрдЦрдХ Deng Z. et al. ┬╖ 2026-09
рдФрд░ рдкрдврд╝реЗрдВ
ЁЯУДPapers

GUIDE: Designer-in-the-loop Authoring of Conformant Generative User Interfaces

September 2026 HCI paper introducing a Figma-based environment for steering generated interfaces toward a designer's intent. GUIDE turns canvas edits into prompt updates and adapts a design-conformance scorer that ranks candidate screens against project references.

generative-uidesign-conformancedesigner-in-the-loop
рд▓реЗрдЦрдХ Lee H. et al. ┬╖ 2026-09
рдФрд░ рдкрдврд╝реЗрдВ

Generative UI resources рдХрд╛ curated рд╕рдВрдЧреНрд░рд╣ред

рдмрдирд╛рдпрд╛ рдЧрдпрд╛ тЭдя╕П community рджреНрд╡рд╛рд░рд╛