Glossary · Models & inference
Autoregressive
A factorization in which each output token is predicted from the tokens that precede it. During generation, the selected token is appended to the sequence and becomes part of the next prediction's context.
Common confusion
The unit is a token, not necessarily a word, and generation can use decoding methods other than always selecting the highest-probability token.
Related terms
Browse the learning paths to see this term in context — every lesson is free to read.