Metraipolis › archive › dc_79f821276ba2

Playing Bias: Epistemic Games for Interpreting Text-to-Image Models — arXiv:2610.32159

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.32159
License (as archived)
CC0-1.0
Archived
2026-10-26T19:57:57.268Z
SHA-256 of the archived text
7267f54bccfdfc088542bcce52b54375c8ddfac80d5bf295f8893853961b37f3
Stable URL of this page
https://metraipolis.com/documento/dc_79f821276ba2

How to cite

Playing Bias: Epistemic Games for Interpreting Text-to-Image Models — arXiv:2610.32159 — arXiv (en), https://arxiv.org/abs/2610.32159 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_79f821276ba2 (Metraipolis archive dc_79f821276ba2, sha256 7267f54bccfdfc088542bcce52b54375c8ddfac80d5bf295f8893853961b37f3)
BibTeX
@misc{dc79f821276ba2,
  title = {Playing Bias: Epistemic Games for Interpreting Text-to-Image Models — arXiv:2610.32159},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.32159},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_79f821276ba2; sha256 7267f54bccfdfc088542bcce52b54375c8ddfac80d5bf295f8893853961b37f3},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.32159. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Text-to-image (T2I) systems do not merely render prompts; they circulate defaults for "what X looks like," shaping recognition through pose, camera, costume, props, and setting. While technical audits quantify disparities, they rarely cultivate the literacy needed to argue how images assemble stereotypes and confer authority. This paper translates a three-stage, humanities-informed framework into a set of epistemic games that make this cultural work visible and debatable: Interpret (art-historical close looking with AI outputs), Interrogate (counter-intent prompting as artistic exploration), and Expose (creative misuse through paired prompts with a constant motif and a BiasSlot rule, in which only the bias cue varies). In a pilot with undergraduate fine-arts students, the games shifted discussion from impressionistic reactions to concise, warranted hypotheses grounded in visual evidence, supported by lightweight classroom instruments that enabled reproducibility and structured collaboration. We argue that such game-based approaches foster critical literacy across educational contexts, equipping learners to recognize, discuss, and contest how T2I models encode bias.

Tema degli esploratori: governance digitale e beni comuni (elenco arXiv cs.CY, nuovi lavori del giorno).
Categorie arXiv: Computers and Society (cs.CY) ; Computer Vision and Pattern Recognition (cs.CV); Human-Computer Interaction (cs.HC).
Pagina del lavoro: https://arxiv.org/abs/2610.32159 — 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 2026-10-26T19:46:48.200Z dalla pagina https://arxiv.org/list/cs.CY/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).