AddressRAG: A Novel Retrieval Method for Toponym and Address Based on Knowledge Graph and Large Language Models
TL;DR
Experiments on a cross‐city dataset showed that AddressRAG obtained higher observed mean scores in faithfulness, answer relevance, candidate retrieval, and administrative hierarchy consistency, with uncertainty quantified using bootstrap confidence intervals.
Abstract
Efficient and precise toponym and address retrieval has become a cornerstone for sectors such as logistics, intelligent navigation, and urban planning. However, conventional address retrieval methods often struggle with semantic ambiguity, incomplete information, or nonstandard address formats, resulting in suboptimal retrieval accuracy and limited robustness. To tackle these challenges, this study proposes AddressRAG, an innovative intelligent retrieval framework that integrates Knowledge Graphs (KG) with Large Language Models (LLM). AddressRAG employs a custom Semantic Text Augmentation (STA) mechanism to enhance the administrative hierarchy and spatial constraints of the raw data. Then we construct an enhanced hierarchical knowledge graph based on prompt tuning. Furthermore, a hierarchical community reporting mechanism was introduced for AddressRAG to accurately capture macro‐level administrative constraints and micro‐level spatial relationships. Experiments on a cross‐city dataset showed that AddressRAG obtained higher observed mean scores in faithfulness, answer relevance, candidate retrieval, and administrative hierarchy consistency, with uncertainty quantified using bootstrap confidence intervals. This research provides critical technical support for scalable and adaptive toponym address retrieval.