用大模型直接生成地理坐标，让模糊地址也能精准定位。
ReaGeo: Reasoning-Enhanced End-to-End Geocoding with LLMs
- 将坐标转为地理编码序列，把定位变成文本生成任务。
- 引入思维链机制，提升对空间关系的推理能力。
- 支持模糊位置和非点状区域，适合复杂地理查询场景。
本文提出 ReaGeo，一种基于大语言模型的端到端地理编码框架，旨在克服传统多阶段方法依赖文本或向量相似性检索地理数据库所导致的流程复杂、错误传播及对结构化地理知识库高度依赖等问题。该方法将地理坐标转化为地理哈希序列，将坐标预测任务重构为文本生成问题，并引入思维链机制增强模型对空间关系的推理能力。此外，采用基于距离偏差的强化学习优化生成准确性。大量实验表明，ReaGeo 能够在单点预测中准确处理明确地址查询，有效解决模糊相对位置查询；同时在非点状几何区域预测上也展现出强大的建模能力，凸显其在地理编码任务中的通用性与泛化性能。
原文摘要 · Abstract (English)
This paper proposes ReaGeo, an end-to-end geocoding framework based on large language models, designed to overcome the limitations of traditional multi-stage approaches that rely on text or vector similarity retrieval over geographic databases, including workflow complexity, error propagation, and heavy dependence on structured geographic knowledge bases. The method converts geographic coordinates into geohash sequences, reformulating the coordinate prediction task as a text generation problem, and introduces a Chain-of-Thought mechanism to enhance the model's reasoning over spatial relationships. Furthermore, reinforcement learning with a distance-deviation-based reward is applied to optimize the generation accuracy. Comprehensive experiments show that ReaGeo can accurately handle explicit address queries in single-point predictions and effectively resolve vague relative location queries. In addition, the model demonstrates strong predictive capability for non-point geometric regions, highlighting its versatility and generalization ability in geocoding tasks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。