An LLM (Large Language Model) is a neural network trained on vast amounts of text that can understand and generate human-like language.
Modern LLMs such as GPT or Claude models are built on the transformer architecture, which lets the model capture relationships between words far apart in a text via an attention mechanism.
During training, the model learns statistical patterns of language from massive amounts of text drawn from the internet, books and other sources – it does not "know" anything in a human sense, but predicts with high accuracy which next word (token) is most likely to follow.
An LLM's size is often measured in billions of parameters; larger models can capture more complex relationships but also require significantly more compute for both training and inference.
