DesignPref: Why AI needs your personal design taste

Kari Jaaskelainen

26 Nov 2025 — 1 min read

TL;DR

AI can now draft UIs and slides, but design taste is personal. DesignPref is a new dataset that captures individual preferences from professional designers—so models can learn your style, not the crowd’s.

What it is: 12k pairwise comparisons of AI-generated UIs, rated by 20 pros with multi-level choices plus written rationales.
Big finding: experts often disagree (Krippendorff’s alpha = 0.25) because they prioritize different aspects like hierarchy, layout, color, and whitespace.
Why it matters: majority-vote “judge” models gloss over individual taste.
What works better: personalization. Fine-tuning or RAG with designer-specific annotations predicts each person’s picks better—using up to 20× fewer examples.
Why it’s new: the first dataset for personalized evaluation of visual design generation.

Paper: https://arxiv.org/abs/2511.20513v1

Authors: Yi-Hao Peng, Jeffrey P. Bigham, Jason Wu

Paper: https://arxiv.org/abs/2511.20513v1

Register: https://www.AiFeta.com

#GenerativeAI #UXDesign #UIDesign #AIDesign #Personalization #HumanCenteredAI #Dataset #DesignResearch

Meet GRACE: a moral governor for safer, more transparent AI

AI agents are getting powerful—so how do we make sure they do the right thing, not just the effective thing? Meet GRACE, a reason-based moral governor that keeps AI behavior aligned with human norms by separating moral reasoning from goal-driven decision-making. * Moral Module: uses deontic logic and explicit reasons

Why some fine-tuned LLMs miss phishing—and how to fix it

Not all fine-tuned LLMs spot phishing equally. A new study tests Llama 3.1 8B, Gemma 2 9B, and Mistral on high-stakes phishing detection—and uses SHAP and mechanistic interpretability to reveal why models do (or don’t) generalize. * Architecture × data diversity matters: Gemma 2 9B hits state-of-the-art performance (F1

AI that explains itself—by following the science

AI that explains itself—by following the science Black-box AI can be powerful, but it often can’t tell us why it made a decision. Concept Bottleneck Models (CBMs) try to fix that by predicting human-understandable concepts first, then the final answer. The catch: standard CBMs ignore domain-specific cause-and-effect and

Meet GenomAgent: A Team of AI Specialists for Smarter Genomics Q&A

TL;DR: Finding reliable answers in genomics is hard. GenomAgent turns one big AI into a coordinating team of specialists—and beats the current leader by 12% on a key benchmark. Genomic facts live across many databases. Standard chatbots struggle because they can’t flexibly query those sources. GeneGPT added

TL;DR

Read more

Meet GRACE: a moral governor for safer, more transparent AI

Why some fine-tuned LLMs miss phishing—and how to fix it

AI that explains itself—by following the science

Meet GenomAgent: A Team of AI Specialists for Smarter Genomics Q&A