A System for Name and Address Parsing with Large Language Models

2026-01-25

AI Summary

This work addresses the challenge of reliably structuring unstructured name and address texts in noisy, multilingual environments. The authors propose a prompt-driven, verification-centric framework that requires no fine-tuning, integrating input normalization, structured prompt engineering, constrained decoding, and deterministic rule-based validation. This approach achieves high-precision, highly consistent information extraction while ensuring reproducibility. Experimental results on real-world heterogeneous address data demonstrate that the method attains strong field-level accuracy, strict adherence to output schemas, and well-calibrated confidence scores across a 17-field structuring task, thereby validating its robustness and scalability.

Technology Category

• Natural Language Processing: Information Extraction
• Machine Learning: Structured Learning
• Planning, Routing, and Scheduling: Planning with Language Models

Application Category

• Web Mining and Content Analysis: Bridging structured and unstructured data
• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies

Abstract

Reliable transformation of unstructured person and address text into structured data remains a key challenge in large-scale information systems. Traditional rule-based and probabilistic approaches perform well on clean inputs but fail under noisy or multilingual conditions, while neural and large language models (LLMs) often lack deterministic control and reproducibility. This paper introduces a prompt-driven, validation-centered framework that converts free-text records into a consistent 17-field schema without fine-tuning. The method integrates input normalisation, structured prompting, constrained decoding, and strict rule-based validation under fixed experimental settings to ensure reproducibility. Evaluations on heterogeneous real-world address data show high field-level accuracy, strong schema adherence, and stable confidence calibration. The results demonstrate that combining deterministic validation with generative prompting provides a robust, interpretable, and scalable solution for structured information extraction, offering a practical alternative to training-heavy or domain-specific models.

Problem

• name parsing
• address parsing
• structured data extraction
• large language models
• information extraction

Innovation

• prompt-driven parsing
• validation-centered framework
• constrained decoding
• structured information extraction
• large language models