DesignPref: Why One-Size-Fits-All AI Design Judges Miss the Mark
TL;DR
People don’t agree on what ‘good’ UI design looks like—and AI shouldn’t assume they do.
DesignPref is a new dataset: 12,000 head-to-head UI design comparisons, each labeled by 20 professional designers with multi-level ratings and short rationales. Designers often disagreed (low agreement), driven by different priorities like layout, typography, color, hierarchy, and personal style.
Why it matters: Training AI judges by majority vote smooths away real, individual taste. The authors show that personalized models—fine-tuned or prompted with designer-specific notes (RAG)—predict a designer’s choices better than ‘average’ models, even with 20× fewer examples.
- First dataset for personalized visual design evaluation
- Challenges the ‘one objective score’ myth in design
- Opens the door to AI that adapts to your taste
Paper: https://arxiv.org/abs/2511.20513
Paper: https://arxiv.org/abs/2511.20513v1
Register: https://www.AiFeta.com
#AI #UXDesign #UIDesign #GenerativeAI #Personalization #HCI #DesignResearch #Datasets
