Metraipolis › archive › dc_59bdbebafa53

NegT2IBench: When Negation Changes the Picture. A Polarity Benchmark for Text-to-Image Models — arXiv:2610.03084

Source: arXiv
Original: https://arxiv.org/abs/2610.03084
License (as archived): CC0-1.0
Archived: 2026-10-05T22:50:25.445Z
SHA-256 of the archived text: 0a3b25a214a04a91dc010038019b4cf3e71bc1ee38c1b9b9ee2251c222da6380
Stable URL of this page: https://metraipolis.com/documento/dc_59bdbebafa53

How to cite

NegT2IBench: When Negation Changes the Picture. A Polarity Benchmark for Text-to-Image Models — arXiv:2610.03084 — arXiv, https://arxiv.org/abs/2610.03084 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_59bdbebafa53 (Metraipolis archive dc_59bdbebafa53, sha256 0a3b25a214a04a91dc010038019b4cf3e71bc1ee38c1b9b9ee2251c222da6380)

BibTeX

@misc{dc59bdbebafa53,
  title = {NegT2IBench: When Negation Changes the Picture. A Polarity Benchmark for Text-to-Image Models — arXiv:2610.03084},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.03084},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_59bdbebafa53; sha256 0a3b25a214a04a91dc010038019b4cf3e71bc1ee38c1b9b9ee2251c222da6380},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.03084. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Text-to-image (T2I) models are judged by benchmarks that measure whether requested content appears, but these benchmarks largely overlook the complementary ability to satisfy negated constraints, for example, generating "a non-red cup." Measuring negation raises challenges not faced by affirmation-based benchmarks and requires careful prompt and evaluation design. We introduce NegT2IBench, a benchmark of 4,800 prompts covering two attribute types and four relation categories. Prompts are organized by polarity: the number of positive statements that must hold and negated statements that must not, each ranging from 0 to 2. Varying the two independently separates the effect of negation from the effect of prompt complexity. Our detector-based scoring is reproducible, auditable, and pinpoints which requirement failed. On 600 images with three-annotator labels, it agrees with humans as closely as vision-language judges up to 30x larger, while using only a fraction of their GPU memory. Across eleven T2I models and 211,200 images, nine score lower on a single negated statement than on a single positive one. Per-statement scoring reveals that the loss is largest for color and near zero for proximity, and that 41.5% of failed statements render exactly what the prompt forbids. Rendering what a prompt asks for and withholding what it forbids are distinct capabilities that an aggregate compositional score cannot distinguish. NegT2IBench measures the latter directly, providing a controlled testbed for diagnosing negation failures and developing methods to overcome them.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.03084 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-05T22:45:55.823Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).