Large Language Models for Geolocation Extraction in Humanitarian Crisis Response

📅 2026-02-09
📈 Citations: 0
Influential: 0
📄 PDF
🤖 AI Summary
This study addresses geographic and socioeconomic biases in existing automated systems for extracting locations from humanitarian texts, which result in uneven visibility of crisis-affected regions. To mitigate this, the authors propose a two-stage framework: first employing a few-shot large language model (LLM) for named entity recognition, followed by an agent-based, context-aware geocoding module for precise toponym disambiguation. This approach represents the first integration of LLMs with fairness principles in humanitarian geospatial analysis. Evaluated on an expanded HumSet dataset, the method significantly outperforms current rule-based and pretrained systems, achieving higher overall accuracy while notably improving location recognition in underrepresented regions, thereby advancing more inclusive and equitable humanitarian response efforts.

Technology Category

Application Category

📝 Abstract
Humanitarian crises demand timely and accurate geographic information to inform effective response efforts. Yet, automated systems that extract locations from text often reproduce existing geographic and socioeconomic biases, leading to uneven visibility of crisis-affected regions. This paper investigates whether Large Language Models (LLMs) can address these geographic disparities in extracting location information from humanitarian documents. We introduce a two-step framework that combines few-shot LLM-based named entity recognition with an agent-based geocoding module that leverages context to resolve ambiguous toponyms. We benchmark our approach against state-of-the-art pretrained and rule-based systems using both accuracy and fairness metrics across geographic and socioeconomic dimensions. Our evaluation uses an extended version of the HumSet dataset with refined literal toponym annotations. Results show that LLM-based methods substantially improve both the precision and fairness of geolocation extraction from humanitarian texts, particularly for underrepresented regions. By bridging advances in LLM reasoning with principles of responsible and inclusive AI, this work contributes to more equitable geospatial data systems for humanitarian response, advancing the goal of leaving no place behind in crisis analytics.
Problem

Research questions and friction points this paper is trying to address.

geolocation extraction
humanitarian crisis
geographic bias
socioeconomic bias
location visibility
Innovation

Methods, ideas, or system contributions that make the work stand out.

Large Language Models
Geolocation Extraction
Few-shot Learning
Fairness-aware AI
Toponym Resolution
🔎 Similar Papers
No similar papers found.
💼 Related Jobs
No related jobs found.
G
G. Cafferata
Universidad de San Andrés, Victoria, Buenos Aires, Argentina
T
T. Demarco
Universidad de San Andrés, Victoria, Buenos Aires, Argentina
K
K. Kalimeri
ISI Foundation, Turin, Italy
Y
Y. Mejova
ISI Foundation, Turin, Italy
M
M. G. Beiró
Universidad de San Andrés, Victoria, Buenos Aires, Argentina; CONICET, Buenos Aires, Argentina