Large language model
A deep neural network trained on vast amounts of text to predict the next token. Fluency follows from that training and accuracy does not, so any figure it states needs checking against the source.
Where you will meet it
Large language model appears in 2 learning outcomes on the CFA syllabus. A few of them:
- Explain how training works for large language models and the way they produce text
“A large language model is a deep neural network trained on text.”
- Explain how investment managers put large language models and generative AI to use
“Generative AI and large language models are used across investment work mainly to handle unstructured text at scale.”
See also
Learn it properly
Practise it
Practise large language model until it is automatic: questions that explain every wrong option.
Take the free diagnostic →