Metraipolis › archive › dc_3f0933fc5f3d

Telling Is Not Seeing: Textual Personas Rarely Make Vision-Language Models Answer Like the People They Describe — arXiv:2610.39331

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.39331
License (as archived)
CC0-1.0
Archived
2026-10-31T06:13:11.084Z
SHA-256 of the archived text
405e20d65edd3d067d19b740c85b2aa7d990c63adfa7ca0ebfe0c0e85d7e981a
Stable URL of this page
https://metraipolis.com/documento/dc_3f0933fc5f3d

How to cite

Telling Is Not Seeing: Textual Personas Rarely Make Vision-Language Models Answer Like the People They Describe — arXiv:2610.39331 — arXiv (en), https://arxiv.org/abs/2610.39331 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3f0933fc5f3d (Metraipolis archive dc_3f0933fc5f3d, sha256 405e20d65edd3d067d19b740c85b2aa7d990c63adfa7ca0ebfe0c0e85d7e981a)
BibTeX
@misc{dc3f0933fc5f3d,
  title = {Telling Is Not Seeing: Textual Personas Rarely Make Vision-Language Models Answer Like the People They Describe — arXiv:2610.39331},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.39331},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3f0933fc5f3d; sha256 405e20d65edd3d067d19b740c85b2aa7d990c63adfa7ca0ebfe0c0e85d7e981a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.39331. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Vision-language models (VLMs) are increasingly prompted with personas, such as "You have low vision", to stand in for people in user studies. We ask whether a persona makes a model see like the person it describes. We compare persona answers with measured people with low vision, color blindness or hearing loss, and with simple rules that use only the facts the persona states. The persona never beats these rules, and it erases the real differences between groups and individuals. Describing blur leaves recognition unchanged in all 14 models we test, while blurring the photo lowers it as it does for people. Inside open models, the description changes neither the image information nor the answer probabilities. Yet the models know the effects they fail to show: they can estimate how blur and illusions affect people. Telling is not seeing: a persona makes a model say what it knows about people, not see what they see.

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).
Pagina del lavoro: https://arxiv.org/abs/2610.39331 — 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 2026-10-31T06:07:08.708Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).