Large language model
Also known as LLM
The kind of AI model behind answer engines, trained on large text corpora to predict and generate language.
A large language model generates text by predicting what comes next, one token at a time, based on patterns learned from training data. ChatGPT, Claude, Gemini, and Grok are all built on LLMs.
On their own, LLMs answer from training and can go stale or invent details. Paired with retrieval, they can ground answers in current sources, which is the setup most answer engines now use.