Short Answer

Computational Scaling in Autoregressive Models

In an autoregressive language model, the probability of the next token is calculated based on the input and all previously generated tokens. Explain why the computational cost of calculating this probability for each new token can become a significant challenge as the generated sequence gets longer. What is the primary source of this increasing computational load?

0

1

Updated 2025-10-10

Contributors are:

Who are from:

Tags

Ch.5 Inference - Foundations of Large Language Models

Foundations of Large Language Models

Foundations of Large Language Models Course

Computing Sciences

Analysis in Bloom's Taxonomy

Cognitive Psychology

Psychology

Social Science

Empirical Science

Science