大型语言模型在人道主义危机响应中的地理信息提取
Large Language Models for Geolocation Extraction in Humanitarian Crisis Response
AI总结：
本文提出基于LLM的两步框架，通过结合命名实体识别和上下文地理编码模块，提升人道主义文档中地理信息提取的精度与公平性。
摘要：
人道主义危机需要及时且准确的地理信息来指导有效的应对行动。然而，从文本中自动提取位置的系统往往复现已有的地理和社会经济偏见，导致危机影响地区可见性不均。本文研究大型语言模型（LLMs）是否能解决这些地理差异，在人道主义文档中提取位置信息。我们介绍了一个两步框架，结合少量样本的LLM基于命名实体识别和一个基于代理的地理编码模块，利用上下文来解决歧义的地名。我们通过准确性和公平性指标在地理和社会经济维度上将我们的方法与最先进的预训练和规则系统进行基准测试。我们的评估使用了扩展版的HumSet数据集，带有经过细化的字面地名注释。结果表明，基于LLM的方法在从人道主义文本中提取地理信息的精度和公平性方面显著提高，特别是对于代表性不足的地区。通过将LLM推理的进展与负责任和包容的AI原则相结合，这项工作为更公平的地理空间数据系统做出了贡献，推动了在危机分析中实现“无一遗漏”的目标。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
