Transformer
Also: transformers
The design most modern language models use. Its trick is letting every word in a passage look at every other word to work out what matters.
The fuller definition
A transformer is a neural-network architecture built around attention mechanisms and other layers that process relationships among elements in a sequence.
Lines represent computational connections with learned values. This tiny diagram illustrates a neural network; a transformer or mixture-of-experts model has additional structures not shown here.
A concrete example
A language model uses surrounding tokens to help represent an ambiguous word before predicting what follows.
The distinction that matters
Not every transformer has the same design, context length, or supported input types.
Related terms
Attention
A way for a model to weigh links between parts of its input. The weights help it process text. They do not show which claims are true.
Documents & retrievalEmbedding
A list of numbers used to compare items such as texts. Texts with similar meanings may have similar lists.
FoundationsLarge language model (LLM)
A program trained on enormous amounts of text so it can read and write language. ChatGPT and Claude are built on large language models.
Where it is taught
What actually happens when you ask AI a question?Source and further reading
Google · Machine Learning GlossaryThe definition and example are written for this library. The link gives background, official documentation or legal authority as labelled. Legal scope depends on the jurisdiction and current text; product features depend on release and settings.