Large Language Model (LLM)
A large language model is a very large neural network trained on vast amounts of text to predict the next word, which allows it to understand and generate human-like language.
What is Large Language Model (LLM)?
LLMs such as GPT, Claude, Gemini and Llama can answer questions, write, summarise, translate and code. They contain billions of parameters and are usually transformers. Most qualify as general-purpose AI models under the EU AI Act. They can also produce confident but false statements.
How it works
An LLM is pre-trained on next-token prediction over trillions of tokens, then fine-tuned with instructions and human feedback to be helpful and safe.
← All Artificial Intelligence & Superintelligence definitions · ← Back to the A–Z definitions