TASTE: A Designer-Annotated Multi-Dimensional Preference Dataset for AI-Generated Graphic Design
The article discusses the release of TASTE, a dataset designed to evaluate AI-generated graphic design. It includes ratings from professional designers on various criteria, highlighting the limitations of existing models in accurately assessing design quality. The findings suggest that while some models perform better than others, none fully meet the standards set by human designers.
- ▪TASTE is a dataset that includes ratings from ten professional designers on outputs from four text-to-image models across nine criteria.
- ▪The dataset aims to address the shortcomings of existing models that rely on single overall verdicts for graphic design evaluation.
- ▪A small pairwise-difference head trained on TASTE achieved a score of 0.611, closing the gap to the single-rater ceiling.
arXiv cs.AI files mainly under ai research. We currently carry 1,128 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | arXiv cs.AI |
| Canonical URL | https://arxiv.org/abs/2605.20731 |
| Publication time | Fri, 22 May 2026 00:00:00 -0400 |
| Retrieval time | 2026-05-22T04:02:00.009Z |
| Last seen | 2026-05-22T04:02:00.009Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | dqHsFGprTTdv |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
Computer Science > Computer Vision and Pattern Recognition arXiv:2605.20731 (cs) [Submitted on 20 May 2026] Title:TASTE: A Designer-Annotated Multi-Dimensional Preference Dataset for AI-Generated Graphic Design Authors:Haonan Zhu, Elad Hirsch, Alexandria Minetti, Allison Nulty, Purvanshi Mehta View a PDF of the paper titled TASTE: A Designer-Annotated Multi-Dimensional Preference Dataset for AI-Generated Graphic Design, by Haonan Zhu and 4 other authors View PDF HTML (experimental) Abstract:Text-to-image models produce graphic design at production scale, but their supervision comes from photo-style preference data with a single overall verdict per comparison.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at arXiv cs.AI.
Discussion
0 commentsMore from arXiv cs.AI
