Metraipolis › archive › dc_2dfb433dc971
From UNDRR Reports to Event Records: Schema-Constrained LLM Extraction of Georeferenced Disasters — arXiv:2609.23853
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.23853
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-09T06:49:56.532Z
- SHA-256 of the archived text
262e033fddd478dac29717e8a83506a336907c9fd383fa0098eb09551a30ddf1- Stable URL of this page
https://metraipolis.com/documento/dc_2dfb433dc971
How to cite
From UNDRR Reports to Event Records: Schema-Constrained LLM Extraction of Georeferenced Disasters — arXiv:2609.23853 — arXiv (en), https://arxiv.org/abs/2609.23853 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2dfb433dc971 (Metraipolis archive dc_2dfb433dc971, sha256 262e033fddd478dac29717e8a83506a336907c9fd383fa0098eb09551a30ddf1)
BibTeX
@misc{dc2dfb433dc971,
title = {From UNDRR Reports to Event Records: Schema-Constrained LLM Extraction of Georeferenced Disasters — arXiv:2609.23853},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.23853},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2dfb433dc971; sha256 262e033fddd478dac29717e8a83506a336907c9fd383fa0098eb09551a30ddf1},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.23853. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Disaster-risk-reduction archives describe hazard events in prose that databases such as EM-DAT (Delforge et al., 2025) cannot ingest directly. We present an LLM pipeline that generates candidate georeferenced event records using a controlled hazard vocabulary and fixed schema, retaining evidence for review. Applied to 10,000 documents from PreventionWeb, the knowledge hub managed by UNDRR, it produced 3,572 records from 1,913 documents across 24 hazard types and resolved 81% of location mentions to OpenStreetMap geometries. On 171 human-positive document windows from a stratified 217-document reference set, GPT-5 achieved 86.0% pooled attribute $F_1$, versus 44.2% for the spaCy-gazetteer baseline. Evaluation pools hazard families, location strings, and event years within documents, without assessing their assignment to individual events. GPT-5.4 ranked highest among ten LLMs (86.6% $F_1$). Verbatim evidence occurrence was 72.0% for GPT-5 and 47.2% for GPT-5.4, measuring textual traceability without establishing attribute support. We report production failure modes and automated label and location-rule compliance checks. Prompts, schema, and outputs will be released for adaptation to national reporting archives. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-22 in cs.CL). Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI); Information Retrieval (cs.IR). Pagina del lavoro: https://arxiv.org/abs/2609.23853 — 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 2026-10-09T06:48:45.011Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).