Embedding model vs Large language model (LLM)

Why they differ

Both read text, but an embedding model returns a single list of numbers, while a large language model writes new text.

Retrieval & search

A model that reads a piece of text and gives back an embedding instead of writing an answer.

Formal

A neural network, usually a transformer, trained so that texts close in meaning come out as embeddings that score high on cosine similarity; it turns both stored documents and incoming questions into embeddings.

In plain English

Like a wine taster who marks every wine on the same flavour chart - light to heavy, sweet to dry - without ever telling you what the label says.

In practice

A developer at a Danish software house runs a pension fund's 3,000 help pages through an embedding model once, stores the results, and runs each member's question through the same model when they search.

Why it matters

Switching to a new one means redoing every stored embedding, since the numbers from two different models cannot be compared - and a model weak in Danish gives weak Danish search.

Large language model (LLM)

Language models

A very large model trained on huge amounts of text to predict the next word, which lets it write, sum up and answer in fluent language.

Formal

A deep learning model, usually a transformer with billions of weights, trained on vast text collections to predict the next token; the same skill, repeated, lets it produce long answers to a prompt.

In plain English

Like the next-word suggestions on a phone keyboard, but trained on a large part of the internet - it knows how answers usually sound, not whether they are true.

In practice

Staff in a municipality get a chat assistant built on an LLM to draft replies to citizens and sum up meeting notes, and the IT department must decide which data they may paste into it.

Why it matters

LLMs sound confident even when wrong, can be steered by hidden text, and send your input to whoever runs them - all real risks to weigh before use.

Shared connections

Transformer