# Fighting crime with Transformers: Empirical analysis of address parsing methods in payment data

arXiv: https://arxiv.org/abs/2404.05632 · HTML: https://mlsanity.com/paper/2404.05632/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 23 references that are in the map.
- First posted on arXiv 8 Apr 2024.

## Builds on (most cited first, 7 of 7)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [Memorization vs. Generalization: Quantifying Data Leakage in NLP Performance Evaluation](https://mlsanity.com/paper/2102.01818/) (2021)
- [NER-BERT: A Pre-trained Model for Low-Resource Entity Tagging](https://mlsanity.com/paper/2112.00405/) (2021)
- [Leveraging Subword Embeddings for Multinational Address Parsing](https://mlsanity.com/paper/2006.16152/) (2020)
- [Deepparse : An Extendable, and Fine-Tunable State-Of-The-Art Library for Parsing Multinational Street Addresses](https://mlsanity.com/paper/2311.11846/) (2023)

## Built on by (most cited first, 2 of 2)

- [A System for Name and Address Parsing with Large Language Models](https://mlsanity.com/paper/2601.18014/) (2026)
- [Entity Extraction from High-Level Corruption Schemes via Large Language Models](https://mlsanity.com/paper/2409.13704/) (2024)

## Abstract (arXiv)

In the financial industry, identifying the location of parties involved in payments is a major challenge in the context of various regulatory requirements. For this purpose address parsing entails extracting fields such as street, postal code, or country from free text message attributes. While payment processing platforms are updating their standards with more structured formats such as SWIFT with ISO 20022, address parsing remains essential for a considerable volume of messages. With the emergence of Transformers and Generative Large Language Models (LLM), we explore the performance of state-of-the-art solutions given the constraint of processing a vast amount of daily data. This paper also aims to show the need for training robust models capable of dealing with real-world noisy transactional data. Our results suggest that a well fine-tuned Transformer model using early-stopping significantly outperforms other approaches. Nevertheless, generative LLMs demonstrate strong zero-shot performance and warrant further investigations.