Search papers, labs, and topics across Lattice.
ReaGeo, an end-to-end geocoding framework, is introduced to address limitations of multi-stage methods by reformulating coordinate prediction as text generation of geohash sequences using LLMs. A Chain-of-Thought mechanism enhances spatial reasoning, and reinforcement learning with a distance-deviation reward optimizes generation accuracy. Experiments demonstrate ReaGeo's ability to handle explicit addresses, resolve vague locations, and predict non-point geometric regions, showcasing its versatility in geocoding.
LLMs can now directly predict geographic coordinates with high accuracy, even for vague locations and complex regions, bypassing the need for traditional geocoding pipelines.
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.
DAMO