Skip to main content
A white text on blue background

The Potential for Large Language Models to Advance Name Matching

Babel Street Chief Scientist Kfir Bar to deliver presentation at AI & Generative AI Summit, May 23, 2023

May 16, 2023 — Name matching, a function critical to watchlist screening, name searching, and connecting disparate data about people and organizations, is getting boost from large language models (LLMs). LLMs are deep learning algorithms that train on massive data sets to learn how to generate text, summarize information, and perform other text-based tasks. ChatGPT is one of the most prominent examples of an LLM.

The inherent variety and ambiguity of names make name matching a challenging task in the realm of natural language processing (NLP). NLP must consider errors and inconsistencies introduced by humans such as spelling errors, missing name components, out-of-order names, and use of initials. Furthermore, names can be written in different languages and scripts or can contain aliases and nicknames.

Kfir Bar, Chief Scientist at Babel Street spoke on “Using Large Language Models (LLMs) for Name Matching,” at the AI & Generative AI Summit on May 23, 2023 in Rishon LeTsiyon, Israel.

Bar introduced a method for name matching using an LLM that works on the byte level, whereby personal names are represented as mathematical vectors. He discussed results from using test sets with multiple scripts and compare the results from the LLM model to more traditional AI-based name matching.

About the AI & Generative AI Summit

This event brings together 500 researchers, data scientists, and developers from academia and industry to discuss state-of-the-art artificial intelligence, generative Al, NLP, deep learning, data science, and applied machine learning. It features more than 35 talks from leading experts and researchers in these fields. The 2023 conference focuses on generative Al challenges and innovations and how AI applies to the real world. The summit deals with a broad spectrum of research and application topics,including generative AI, AI case studies and innovations, NLP and human language understanding, machine learning, and deep learning. See for more information

About Babel Street

Babel Street provides the most advanced data analytics and decision intelligence platform for the world’s most trusted government and commercial organizations. The AI-enabled platform helps them stay informed and improves around-the-clock decision-making for threat intelligence, identity and risk management, and alerting use cases. Teams are empowered to rapidly detect and collaborate on what matters in seconds by transforming massive amounts of multilingual, publicly available data into actionable insights so they can act with confidence. Babel Street is headquartered in the U.S. with offices near Washington, D.C. and Boston, along with Tokyo, Tel Aviv, London, Canberra, and Ottawa. For more information, visit

Babel Street Home
Trending Searches