Case Study

Calculating Consecutively Accepted Tokens

In a text generation process, a sequence of 4 candidate tokens is proposed. For each token, a random number is drawn and compared to a probability ratio to determine if the token is accepted or rejected. A token at index t is rejected if its corresponding random number r_t is greater than its probability ratio. The process stops at the first rejected token, and the number of consecutively accepted tokens from the start is counted.

Based on the data provided below, what is the final count of consecutively accepted tokens?

0

1

Updated 2025-09-26

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

Application in Bloom's Taxonomy

Cognitive Psychology

Psychology

Social Science

Empirical Science

Science