Short Answer

Interpreting Model Certainty from Ranked Probabilities

A language model is tasked with completing a sentence. In one instance (Case A), the ranking stage produces the following top three candidates: 'happy' (Pr=0.8), 'glad' (Pr=0.05), 'joyful' (Pr=0.02). In another instance (Case B), the ranking stage produces: 'run' (Pr=0.35), 'walk' (Pr=0.32), 'sprint' (Pr=0.30). Compare the distribution of probabilities after ranking in Case A versus Case B. What does this difference suggest about the model's certainty for its top choice in each case?

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