Large language model (LLM)
Definition
A large language model is a statistical model trained on very large text corpora that predicts likely continuations of text. It can classify, summarise, translate and draft, and it is the reasoning component inside most AI agents — but it holds no live company data by itself.
An LLM is a component, not a system. On its own it has no access to your orders, contracts or master data, and it has a knowledge cut-off. Business value appears when the model is connected to authoritative company data and to systems it can write to.
Model choice is an engineering decision: cost per token, latency, context window, language coverage and the hosting region all matter more than benchmark leaderboards.
In practice
- Provides judgement, language and extraction — not facts about your business
- Needs retrieval or tool access to work with current company data
- Model selection is driven by cost, latency, language and data location
Related terms
- Retrieval-augmented generation (RAG)Retrieval-augmented generation is a method in which relevant company documents are searched first and the retrieved passages are given to the language model as context. The model answers from those passages, which makes answers current, source-linked and auditable.
- HallucinationA hallucination is a confident but false output from a language model — an invented figure, clause or reference. It is a property of statistical text generation, which is why production systems verify outputs against source data instead of trusting them.
- Fine-tuningFine-tuning further trains an existing model on company-specific examples so it adopts a style, format or classification behaviour. It changes how a model responds, not what current facts it knows, and is usually the last option after prompting and retrieval.