Large language model
Definition
A very large neural network trained on huge amounts of text to predict the next piece of text, which lets it write, summarize, and answer questions.
In plain English
At its core, an LLM has one skill: given some text, guess what comes next. Trained on enough text, that one skill turns into many: answering questions, translating, writing code, and explaining ideas.
Because it predicts likely text rather than looking up facts, an LLM can sound confident while being wrong. That’s called a hallucination.
Example
When you ask a chatbot to summarize an article, a large language model generates the summary one token at a time, each time picking a likely next word.
Draft, not yet reviewed by a person · Updated Nov 2026