Metraipolis › archive › dc_694a84bed3aa

Toward Cultural Alignment: Human-Centered Evaluation of Multimodal AI Stories Across Five African Communities — arXiv:2608.29209

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.29209
License (as archived)
CC0-1.0
Archived
2026-10-17T08:06:53.454Z
SHA-256 of the archived text
33f658adc32d2d7efbdc0284485e2fa3e963dd478304743fa11b385de79d3b04
Stable URL of this page
https://metraipolis.com/documento/dc_694a84bed3aa

How to cite

Toward Cultural Alignment: Human-Centered Evaluation of Multimodal AI Stories Across Five African Communities — arXiv:2608.29209 — arXiv (en), https://arxiv.org/abs/2608.29209 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_694a84bed3aa (Metraipolis archive dc_694a84bed3aa, sha256 33f658adc32d2d7efbdc0284485e2fa3e963dd478304743fa11b385de79d3b04)
BibTeX
@misc{dc694a84bed3aa,
  title = {Toward Cultural Alignment: Human-Centered Evaluation of Multimodal AI Stories Across Five African Communities — arXiv:2608.29209},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.29209},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_694a84bed3aa; sha256 33f658adc32d2d7efbdc0284485e2fa3e963dd478304743fa11b385de79d3b04},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.29209. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

In this paper, we examine how well AI-generated multimodal stories align with the lived practices, relationships, language, values, and visual expectations of the communities they represent. We conduct a community-grounded mixed-methods evaluation with 19 culture representatives across five African communities, combining quantitative annotations with qualitative focus group discussions. We find that cultural alignment depends not simply on recognizable cultural markers, but on how those markers fit social, linguistic, procedural, and visual context. From these evaluations, we develop a taxonomy of cultural alignment comprising five broader cultural marker categories and eight recurring mechanisms of misalignment. We additionally evaluate five multimodal LLM judges to examine whether automated evaluation can approximate community-grounded judgments at scale. Judge reliability and score calibration vary substantially across communities, with no single judge performing consistently across all five settings. These findings motivate community-calibrated evaluation pipelines in which automated judges are validated against community judgments to determine where they can be trusted and where human review remains necessary.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-01 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL) ; Human-Computer Interaction (cs.HC).
Pagina del lavoro: https://arxiv.org/abs/2608.29209 — 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 2026-10-17T07:47:52.678Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).