{
  "abstract": "Text-to-image models now generate graphic design at production scale, yet their supervision still comes primarily from photo-style preference datasets with a single overall verdict per comparison. Designers evaluate designs along several distinct axes (e.g., typography, layout, color harmony) that a single preference label collapses. We release \\emph{TASTE} \\textit{(Typography, Aesthetics, Spatial, Tone, Etc.)}, a multi-dimensional preference dataset in which two disjoint cohorts of five professional designers each ranked outputs from four current text-to-image models across nine criteria along with per-image hallucination flags. We pair the dataset with two contributions. First, a criterion-agnostic signal-validation framework based on Kendall's $τ$, majority-vote probability, and Condorcet cycles against exact iid-uniform nulls; the analysis reveals significant but moderate designer agreement, with every TASTE criterion rejecting the random-rater null. Second, we benchmark preference models on TASTE and find that off-the-shelf VLM judges and dedicated T2I scorers fail to reach majority agreement with the designer panel, while a small MLP head trained directly on TASTE substantially narrows the gap to the single-rater ceiling, setting a baseline for future TASTE-trained preference models.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2605.20731",
  "author_total": 6,
  "authors": [
    {
      "name": "Haonan Zhu"
    },
    {
      "name": "Elad Hirsch"
    },
    {
      "name": "Alexandria Minetti"
    },
    {
      "name": "Allison Nulty"
    },
    {
      "name": "Ben Huffman"
    },
    {
      "name": "Purvanshi Mehta"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/63f241210aymk.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2605.20731",
  "fulltext_url": null,
  "id": "63f241210aymk",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2605.20731",
  "language": null,
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "http://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.AI"
    ],
    [
      "arxiv",
      "cs.CV"
    ],
    [
      "arxiv",
      "stat.AP"
    ],
    [
      "openalex",
      "1707|Generative Adversarial Networks and Image Synthesis"
    ]
  ],
  "openalex": "W7161967792",
  "pdf_url": "https://arxiv.org/pdf/2605.20731",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-21",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/63f241210aymk.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:23:33Z",
      "native_id": "2605.20731",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2605.20731"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:stat.AP",
      "subfield": "statistics"
    }
  ],
  "title": "TASTE: A Designer-Annotated Multi-Dimensional Preference Dataset for AI-Generated Graphic Design",
  "title_text": "TASTE: A Designer-Annotated Multi-Dimensional Preference Dataset for AI-Generated Graphic Design",
  "type": "preprint",
  "updated_at": "2026-10-30T12:23:33Z",
  "url": "https://research.draconitic.com/paper/63f241210aymk",
  "venue": "arXiv",
  "versions": []
}