Metraipolis › archive › dc_c723620472bc

Beauty is in the AI of the beholder: MLLMs systematically overrate facial attractiveness — arXiv:2609.02512

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.02512
License (as archived)
CC0-1.0
Archived
2026-10-17T04:44:32.250Z
SHA-256 of the archived text
d82588334903ac77bdda86986ea882b4bc64d1434c6fed57659f2a374b166e7c
Stable URL of this page
https://metraipolis.com/documento/dc_c723620472bc

How to cite

Beauty is in the AI of the beholder: MLLMs systematically overrate facial attractiveness — arXiv:2609.02512 — arXiv (en), https://arxiv.org/abs/2609.02512 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c723620472bc (Metraipolis archive dc_c723620472bc, sha256 d82588334903ac77bdda86986ea882b4bc64d1434c6fed57659f2a374b166e7c)
BibTeX
@misc{dcc723620472bc,
  title = {Beauty is in the AI of the beholder: MLLMs systematically overrate facial attractiveness — arXiv:2609.02512},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.02512},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c723620472bc; sha256 d82588334903ac77bdda86986ea882b4bc64d1434c6fed57659f2a374b166e7c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.02512. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Beauty assessments from Multimodal Large Language Models (MLLMs) are increasingly popular amongst users, companies, and aestheticians. This raises the question of whether these AI models can accurately reflect human judgments of attractiveness. In a pre- registered exploratory study, we compared the attractiveness ratings of 2,513 human participants to four widely used commercial AI models: Claude, Gemini, GPT, and Grok. Results showed that MLLMs systematically rate faces more favourably and within a narrower range than humans and, at the time of study, do not reproduce human ratings in absolute terms. However, MLLMs exhibit strong correlations with human attractiveness judgments, accurately tracking the rank-ordering of faces. MLLMs may judge faces by different cues than humans; only face age was a predictor of facial attractiveness in both humans and MLLMs, with inconsistent patterns across models for ethnicity and gender. AI models strongly agree with one another, except for Grok, which also showed the lowest agreement with humans. Our findings suggest that while they may be able to approximate rank-orderings of human attractiveness, current off-the-shelf commercial MLLMs systematically overrate the beauty of human faces.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-03 in cs.HC).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Human-Computer Interaction (cs.HC).
Pagina del lavoro: https://arxiv.org/abs/2609.02512 — 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 2026-10-17T04:09:22.124Z dalla pagina https://arxiv.org/catchup/cs.HC/2026-09-03?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).