Learn Before
Case Study

Analyzing the Impact of the 'K' Parameter on Token Selection

Two language models are generating a continuation for the phrase: 'The best way to start the day is with a cup of...'. Both models use the same operator to select a set of the most probable next tokens before making a final choice. However, Model A is configured to select the top 2 candidates (K=2), while Model B is configured to select the top 5 candidates (K=5). Given the following simplified probability distribution over the vocabulary, identify the candidate set for each model and analyze how the difference in the size of 'K' influences the potential for generating either a predictable or a creative response.

0

1

Updated 2025-10-07

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