autoregressive

A model structure or generation method that predicts each next token conditioned on everything generated so far.

1 articleLast mentioned

Autoregressive refers to a model structure or generation method in which each next value is predicted conditioned on the outputs produced so far. In language models, the tokens generated up to that point are fed back as input, the model computes a probability distribution over the next token, one token is sampled and appended, and the process repeats to produce text.

Most large language models, including the GPT family, generate text autoregressively. Because tokens are produced one at a time in sequence, computation grows with output length, which is a major factor in generation latency and cost. In statistics, the term refers to autoregressive models that explain the current value of a time series using its past values.

This entry is based on AIPOST articles and widely known facts. If something is wrong, please send us a correction request.

Articles covering this entry

  • Decision Models: Probabilities, Not Text, for Faster and Cheaper Agent RoutingAI in Practice ·

    A standard chat model runs an autoregressive loop: compute a probability distribution over its whole vocabulary, sample one token, append it, and repeat until t…

    Read article

Found a mistake or missing an entry?

Wiki entries are based on AIPOST articles and widely known facts. If an entry is wrong, send us a correction request and we will check and fix it. Names from new articles are added to the wiki after the article is published.