Case Study

Comparing Model Confidence via Probability Normalization

Two language models, Model A and Model B, are tasked with predicting the next word for the same context. They both consider the same set of three candidate words. The unnormalized scores they produce are listed below. Analyze the outputs of both models. After normalizing the scores for each model to create a probability distribution over the candidate set, determine which model is more 'confident' in its top prediction and justify your answer based on the calculated probabilities.

0

1

Updated 2025-10-08

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

Evaluation in Bloom's Taxonomy

Cognitive Psychology

Psychology

Social Science

Empirical Science

Science