Bloomberg Unveils BloombergGPT which outperforms by “significant margins”

Generative Pre-trained Transformer (GPT), a type of language model that uses deep learning to generate human-like, has moved into finance at scale. Yet, BloombergGPT has been born: “Bloomberg today released a research paper detailing the development of BloombergGPT, a new large-scale generative artificial intelligence (AI) model. This large language model (LLM) has been specifically trained on a wide range of financial data to support a diverse set of natural language processing (NLP) tasks within the financial industry.”  According to Bloomberg, “BloombergGPT outperforms similarly-sized open models on financial NLP tasks by significant margins — without sacrificing performance on general LLM benchmarks”. AI is taking over this world.

Recent advances in Artificial Intelligence (AI) based on LLMs have already demonstrated exciting new applications for many domains. However, the complexity and unique terminology of the financial domain warrant a domain-specific model. BloombergGPT represents the first step in the development and application of this new technology for the financial industry. This model will assist Bloomberg in improving existing financial NLP tasks, such as sentiment analysis, named entity recognition, news classification, and question answering, among others. Furthermore, BloombergGPT will unlock new opportunities for marshalling the vast quantities of data available on the Bloomberg Terminal to better help the firm’s customers, while bringing the full potential of AI to the financial domain.

For more than a decade, Bloomberg has been a trailblazer in its application of AI, Machine Learning, and NLP in finance. Today, Bloomberg supports a very large and diverse set of NLP tasks that will benefit from a new finance-aware language model. Bloomberg researchers pioneered a mixed approach that combines both finance data with general-purpose datasets to train a model that achieves best-in-class results on financial benchmarks, while also maintaining competitive performance on general-purpose LLM benchmarks.

To achieve this milestone, Bloomberg’s ML Product and Research group collaborated with the firm’s AI Engineering team to construct one of the largest domain-specific datasets yet, drawing on the company’s existing data creation, collection, and curation resources. As a financial data company, Bloomberg’s data analysts have collected and maintained financial language documents over the span of forty years. The team pulled from this extensive archive of financial data to create a comprehensive 363 billion token dataset consisting of English financial documents.

This data was augmented with a 345 billion token public dataset to create a large training corpus with over 700 billion tokens. Using a portion of this training corpus, the team trained a 50-billion parameter decoder-only causal language model. The resulting model was validated on existing finance-specific NLP benchmarks, a suite of Bloomberg internal benchmarks, and broad categories of general-purpose NLP tasks from popular benchmarks (e.g., BIG-bench Hard, Knowledge Assessments, Reading Comprehension, and Linguistic Tasks). Notably, the BloombergGPT model outperforms existing open models of a similar size on financial tasks by large margins, while still performing on par or better on general NLP benchmarks.

Register for Tekedia Mini-MBA (Feb 10 - May 3, 2025), and join Prof Ndubuisi Ekekwe and our global faculty; click here.