A System for Name and Address Parsing with Large Language Models
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917223405191168 |
|---|---|
| author | Tarannum, Adeeba Mohammed, Muzakkiruddin Ahmed Cakmak, Mert Can Mandalawi, Shames Al Talburt, John |
| author_facet | Tarannum, Adeeba Mohammed, Muzakkiruddin Ahmed Cakmak, Mert Can Mandalawi, Shames Al Talburt, John |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_18014 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | A System for Name and Address Parsing with Large Language Models Tarannum, Adeeba Mohammed, Muzakkiruddin Ahmed Cakmak, Mert Can Mandalawi, Shames Al Talburt, John Computation and Language Artificial Intelligence 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. |
| title | A System for Name and Address Parsing with Large Language Models |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2601.18014 |