Clemencia Siro, Laura Hollink · 2026 · arXiv
DOI: 10.48550/arXiv.2610.31193 · open-access PDF
Metadata-conditioned generation sering dibingkai sebagai tugas data-to-tekst di mana bidang input tambahan harus meningkatkan grounding. Museum description generation menantang asumsi ini karena catatan katalog heterogen, sebagian visual, dan tidak seimbang didokumentasikan di seluruh wilayah geografis. Kami mempelajari bagaimana komposisi metadata membentuk generasi deskripsi artefak melalui kerangka kerja dua fase. Fase 1 menganalisis variasi metadata alami dalam koleksi museum besar, di mana jumlah medan, jenis medan, ketersediaan gambar, dan tempat ko-variasi.
Machine translation (Meta M2M100); the English original follows.
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
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.31193, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange