# LLM: what it is and how it works · Zorraquino
> An LLM, or large language model, is a machine learning model trained to process and generate language at scale.
URL: https://www.zorraquino.com/en/dictionary/llm

# LLM

An LLM, or large language model, is a machine learning model trained to process and generate language at scale

What it means, how it is used and where it comes up, with its related concepts.

[The whole glossary](https://www.zorraquino.com/en/dictionary)

## What it is and how it works

It uses learnt patterns to produce sequences of tokens and can support tasks such as summarising, classifying or drafting. Some systems extend its capabilities with tools or external information. An LLM is not a reliable database by default: it can generate incorrect statements and needs evaluating in each application.

Also known as

Large language model

Topics

[Artificial intelligence](https://www.zorraquino.com/en/dictionary/category/inteligencia-artificial)

## Related concepts

- [Artificial intelligence](https://www.zorraquino.com/en/dictionary/internet/artificial-intelligence.html)
- [Generative AI](https://www.zorraquino.com/en/dictionary/generative-ai)
- [Token (AI)](https://www.zorraquino.com/en/dictionary/ai-token)
- [RAG](https://www.zorraquino.com/en/dictionary/rag)