Mark Dredze (Johns Hopkins University) “BloombergGPT: A Large Language Model for Finance”

When:
September 18, 2023 @ 12:00 pm – 1:15 pm
2023-09-18T12:00:00-04:00
2023-09-18T13:15:00-04:00
Where:
Hackerman Hall B17
3400 N. Charles Street
Baltimore
MD 21218
Cost:
Free

Abstract

The use of NLP in the realm of financial technology is broad and complex, with applications ranging from sentiment analysis and named entity recognition to question answering. Large Language Models (LLMs) have been shown to be effective on a variety of tasks; however, no LLM specialized for the financial domain has been reported in the literature. In this work, we present BloombergGPT, a 50 billion parameter language model that is trained on a wide range of financial data. We construct a 363 billion token dataset based on Bloomberg’s extensive data sources, perhaps the largest domain-specific dataset yet, augmented with 345 billion tokens from general-purpose datasets.  We validate BloombergGPT on standard LLM benchmarks, open financial benchmarks, and a suite of internal benchmarks that most accurately reflect our intended usage. Our mixed dataset training leads to a model that outperforms existing models on financial tasks by significant margins without sacrificing performance on general LLM benchmarks. Additionally, we explain our modeling choices, training process, and evaluation methodology.

Biography

Mark Dredze is the John C Malone Professor of Computer Science at Johns Hopkins University and the Director of Research (Foundations of AI) for the JHU AI-X Foundry. He develops Artificial Intelligence Systems based on natural language processing and explores applications to public health and medicine.

Prof. Dredze is affiliated with the Malone Center for Engineering in Healthcare, the Center for Language and Speech Processing, among others. He holds a joint appointment in the Biomedical Informatics & Data Science Section (BIDS), under the Department of Medicine (DOM), Division of General Internal Medicine (GIM) in the School of Medicine. He obtained his PhD from the University of Pennsylvania in 2009.

Center for Language and Speech Processing