An LLM-driven extraction pipeline identifies urban datasets in scientific papers at scale, yielding a public portal with 60,000+ structured datasets and reported 90% recall plus 80% field precision.
Jarmin, Frauke Kreuter, and Julia Lane
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Paper2Data: Large-Scale LLM Extraction and Metadata Structuring of Global Urban Data from Scientific Literature
An LLM-driven extraction pipeline identifies urban datasets in scientific papers at scale, yielding a public portal with 60,000+ structured datasets and reported 90% recall plus 80% field precision.