• BloombergGPT is a 50 billion parameter language model trained on a wide range of financial data.
  • The model outperforms existing models on financial tasks without sacrificing performance on general LLM benchmarks.

Key terms:

  • NLP: Natural Language Processing
  • LLM: Large Language Model
  • BloombergGPT: A 50 billion parameter language model for financial applications
  • Financial tasks: Tasks related to financial technology, such as sentiment analysis, named entity recognition, and question answering
  • Mixed dataset training: Combining domain-specific and general-purpose datasets for training


Research Language Model Training Dataset Benchmarks BloombergGPT Question Answering Finance Financial Technology Chronicles