Case Study

Comparing Model Confidence via Log-Likelihood

Two language models, Model A and Model B, are given the same input context and generate the exact same two-token output sequence: y = (y₁, y₂). The models provide the following conditional log-probabilities for each step of the generation process. Based on this data, which model assigned a higher probability to the complete output sequence? Justify your answer by calculating the total log-likelihood for each model.

0

1

Updated 2025-10-04

Contributors are:

Who are from:

Tags

Ch.4 Alignment - 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