Showing cs.CLShow all
2 papers · 1 filter
cs.CL2026
QuanReview: Offline, Auditable Reconciliation of Human and LLM Span Annotations
Matteo Musacchio, Juan Cruz Giner Pulero, Isabel Castañeda +4
Structured span annotations, such as quantities with their units, uncertainty modifiers, and event classes, are expensive to create and hard to keep trustworthy once language model…
cs.CL2026
Large Language Models for Geolocation Extraction in Humanitarian Crisis Response
G. Cafferata, T. Demarco, K. Kalimeri +2
Humanitarian crises demand timely and accurate geographic information to inform effective response efforts. Yet, automated systems that extract locations from text often reproduce…