Large language model (LLM)
An artificial intelligence model trained on a large body of text and able to generate and process text.
Glossary · Automation & AI
A large language model (LLM) is the technology behind chat assistants and many current AI tools. It predicts what text should come next, and on that basis answers questions, summarises, translates, classifies or writes code.
A model does not know your company’s data until it is given it, and has no memory between conversations unless one is built separately. Its knowledge ends at the date of its training data.
The property that matters most in practice is that a model always produces an answer, even when it has nothing to base one on. It therefore suits tasks whose result can be checked or where a mistake is cheap, while important decisions need a person to review them.