# Large Language Models for Geolocation Extraction in Humanitarian Crisis Response

arXiv: https://arxiv.org/abs/2602.08872 · HTML: https://mlsanity.com/paper/2602.08872/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 55 references that are in the map.
- First posted on arXiv 9 Feb 2026.

## Builds on (most cited first, 19 of 19)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines](https://mlsanity.com/paper/2310.03714/) (2023)
- [Large Language Models for Generative Information Extraction: A Survey](https://mlsanity.com/paper/2312.17617/) (2023)
- [Let Me Speak Freely? A Study on the Impact of Format Restrictions on Performance of Large Language Models](https://mlsanity.com/paper/2408.02442/) (2024)
- [Large Language Models are Geographically Biased](https://mlsanity.com/paper/2402.02680/) (2024)
- [InstructionNER: A Multi-Task Instruction-Based Generative Framework for Few-shot NER](https://mlsanity.com/paper/2203.03903/) (2022)
- [Geo-knowledge-guided GPT models improve the extraction of location descriptions from disaster-related social media messages](https://mlsanity.com/paper/2310.09340/) (2023)
- [Man is to Person as Woman is to Location: Measuring Gender Bias in Named Entity Recognition](https://mlsanity.com/paper/1910.10872/) (2019)
- [StructEval: Benchmarking LLMs' Capabilities to Generate Structural Outputs](https://mlsanity.com/paper/2505.20139/) (2025)
- [Assessing Demographic Bias in Named Entity Recognition](https://mlsanity.com/paper/2008.03415/) (2020)
- [Towards LLMs Robustness to Changes in Prompt Format Styles](https://mlsanity.com/paper/2504.06969/) (2025)
- [Harnessing Large Language Models for Disaster Management: A Survey](https://mlsanity.com/paper/2501.06932/) (2025)
- [A Pragmatic Guide to Geoparsing Evaluation](https://mlsanity.com/paper/1810.12368/) (2018)
- [Improving Toponym Resolution with Better Candidate Generation, Transformer-based Reranking, and Two-Stage Resolution](https://mlsanity.com/paper/2305.11315/) (2023)
- [Unequal Opportunities: Examining the Bias in Geographical Recommendations by Large Language Models](https://mlsanity.com/paper/2504.05325/) (2025)
- [Evaluation of Geographical Distortions in Language Models](https://mlsanity.com/paper/2404.17401/) (2024)
- [Leave no Place Behind: Improved Geolocation in Humanitarian Documents](https://mlsanity.com/paper/2309.02914/) (2023)
- [Evaluating Named Entity Recognition Models for Russian Cultural News Texts: From BERT to LLM](https://mlsanity.com/paper/2506.02589/) (2025)

## Built on by (most cited first, 1 of 1)

- [From UNDRR Reports to Event Records: Schema-Constrained LLM Extraction of Georeferenced Disasters](https://mlsanity.com/paper/2609.23853/) (2026)

## Abstract (arXiv)

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.