Large language model (LLM)

A large language model (LLM) is a machine-learning model trained on very large text corpora to predict the next unit of text. That simple objective, at scale, produces systems that can draft, summarize, translate, answer questions, and call tools.

LLMs do not "look things up" by default - they generate a statistically likely continuation from their training. That is why techniques like retrieval-augmented generation and tool use exist: to ground the model in real, current data.