Case Study

Calculating Next-Token Probability

An autoregressive model is generating a sequence of text. After processing the context, it must decide on the next token. The model has computed the following unnormalized scores (logits) for a small set of candidate tokens: {'apple': 2.0, 'banana': 3.0, 'cherry': 1.0}. Based on these scores, calculate the conditional probability for the token 'banana'. Show the main components of your calculation.

0

1

Updated 2025-09-28

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