Metraipolis › archive › dc_9fa68acf71e9

IMPLICIT-Bench: Measuring Implicit Bias in Text-to-Image Models under Neutral Prompts — arXiv:2609.24228

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.24228
License (as archived)
CC0-1.0
Archived
2026-10-09T22:05:33.516Z
SHA-256 of the archived text
0369ad9a57288ee3d6b2d2f68cefc02b87a7db7e8f6033b62650e73f4d84411a
Stable URL of this page
https://metraipolis.com/documento/dc_9fa68acf71e9

How to cite

IMPLICIT-Bench: Measuring Implicit Bias in Text-to-Image Models under Neutral Prompts — arXiv:2609.24228 — arXiv (en), https://arxiv.org/abs/2609.24228 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_9fa68acf71e9 (Metraipolis archive dc_9fa68acf71e9, sha256 0369ad9a57288ee3d6b2d2f68cefc02b87a7db7e8f6033b62650e73f4d84411a)
BibTeX
@misc{dc9fa68acf71e9,
  title = {IMPLICIT-Bench: Measuring Implicit Bias in Text-to-Image Models under Neutral Prompts — arXiv:2609.24228},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.24228},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_9fa68acf71e9; sha256 0369ad9a57288ee3d6b2d2f68cefc02b87a7db7e8f6033b62650e73f4d84411a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.24228. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Text-to-image (T2I) models are typically evaluated for bias using slot-based templates such as ``a photo of a [profession]''. Such templates probe only \emph{explicit} demographic attributes (e.g., gender, skin tone) in isolation. They overlook a broader \emph{implicit} bias that arises in natural prompts: when stereotype-relevant attributes are left unspecified, models still default to stereotypical outputs. We introduce IMPLICIT-Bench, a benchmark for measuring implicit bias in T2I models under such prompts. The key design is a structured-knowledge-graph (KG) construction of controlled prompt triplets: neutral, stereotype, and anti-stereotype variants that differ only along a single bias dimension while preserving scene semantics. This enables precise attribution of bias effects that template benchmarks cannot achieve. IMPLICIT-Bench comprises 5,493 prompts across 11 bias categories, validated through multi-model agreement, CLIP-based verification, and human evaluation. Using this benchmark, we show that state-of-the-art T2I models exhibit systematic bias under neutral prompts, a failure mode largely invisible to existing evaluations. We then use IMPLICIT-Bench to evaluate debiasing methods, uncovering a fundamental trade-off between bias reduction and semantic fidelity.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-22 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.24228 — 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 2026-10-09T21:45:21.018Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).