Large language model (LLM)
Also called LLM, Language model
A large language model (LLM) is an AI model trained on very large amounts of text to predict and generate language. It can answer questions, summarize, translate and write. Its general knowledge comes from training data with a cutoff date, so it needs supplied documents to answer accurately about a specific business.
Example
Claude, GPT and Gemini model families are LLMs; each powers chat assistants and many business tools built on top of them.
Why it matters for a website chatbot
An LLM is the engine inside a modern chatbot, but on its own it knows nothing about your business. ChatBento combines an LLM with retrieval from your content, so answers come from your pages rather than the model's general knowledge.
See it in practice: After-hours support
Related terms
- TokenA token is the unit of text a language model reads and writes: a whole word, part of a word, a number or a punctuation mark. In English, one token averages about three-quarters of a word. AI providers measure context windows, speed and usage-based prices in tokens.
- Context windowA context window is the maximum amount of text, measured in tokens, that a language model can take into account at once. It covers the instructions, the conversation so far, any retrieved documents and the reply being written. Anything outside the window is invisible to the model when it generates its answer.
- Retrieval-augmented generation (RAG)Retrieval-augmented generation (RAG) is a technique in which an AI system first retrieves relevant passages from a chosen set of documents, then gives them to a language model to write its answer. It lets the model answer from current, specific information it was never trained on, and makes answers easier to check.
- HallucinationA hallucination is an output from an AI model that sounds confident and plausible but is false or unsupported by its sources, such as an invented fact, quote, price, policy or link. It happens because language models generate likely-sounding text and have no built-in way to know when they lack information.