# What is a large language model?

Japanese: 大規模言語モデル (だいきぼげんごモデル)

**In one line:** A large language model (LLM) is a large AI model trained on huge amounts of text that generates and understands writing by predicting the next word from the context.

A large language model is an AI that has read a huge amount of writing. It learned how words go together. It is also called an LLM. At its heart, it guesses one thing: “What word is likely to come next?” It does this again and again. So it builds sentences one word at a time. Very large models can answer questions, sum up texts and even write programs. Many AIs that are good at chatting are built this way. Its whole job is guessing the next word. Some people do that in meetings too.

**Common mix-up:** It doesn’t store answers like a dictionary. It builds each sentence fresh from the word patterns it has learned.

**FAQ**

- Does an LLM memorize its answers? — No. It builds each sentence fresh from the patterns it has learned.

Topic: Tech
Published: 2026-11-15
Source URL: https://eli5.net/en/w/llm
日本語: https://eli5.net/w/llm
