Metraipolis › archive › dc_2d7690386f4c
When More Metadata Misleads: Probing Field-Level Grounding in LLM-Generated Museum Descriptions — arXiv:2610.31193
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.31193
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-25T08:34:53.318Z
- SHA-256 of the archived text
2ac3e3fc767985acb48384ab779ba9e0fab9c475985170cee8c067ae03512e31- Stable URL of this page
https://metraipolis.com/documento/dc_2d7690386f4c
How to cite
When More Metadata Misleads: Probing Field-Level Grounding in LLM-Generated Museum Descriptions — arXiv:2610.31193 — arXiv (en), https://arxiv.org/abs/2610.31193 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2d7690386f4c (Metraipolis archive dc_2d7690386f4c, sha256 2ac3e3fc767985acb48384ab779ba9e0fab9c475985170cee8c067ae03512e31)
BibTeX
@misc{dc2d7690386f4c,
title = {When More Metadata Misleads: Probing Field-Level Grounding in LLM-Generated Museum Descriptions — arXiv:2610.31193},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.31193},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2d7690386f4c; sha256 2ac3e3fc767985acb48384ab779ba9e0fab9c475985170cee8c067ae03512e31},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.31193. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Metadata-conditioned generation is often framed as a data-to-text task in which additional input fields should improve grounding. Museum description generation challenges this assumption because catalogue records are heterogeneous, partially visual, and unevenly documented across geographic regions. We study how metadata composition shapes the generation of artefact descriptions through a two-phase framework. Phase 1 analyses natural metadata variation in a large museum collection, where field count, field type, image availability, and Place co-vary. Phase 2 introduces controlled field probes that hold object identity fixed while varying metadata quantity, field type, and image access. Our results show that metadata quantity alone does not explain generation behaviour. Field type determines whether models ground, omit, or infer information, while images can both support visual grounding and increase unsupported interpretation. More broadly, our findings show that metadata-conditioned data-to-text evaluation should assess field- and claim-level support, rather than relying only on aggregate input coverage or reference similarity. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI); Digital Libraries (cs.DL); Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2610.31193 — 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 2026-10-25T08:31:13.233Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).