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
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
Related
Mathematical Formulation of LLM Inference
Equivalence of Maximizing Auto-regressive Log-Likelihood and Minimizing Cross-Entropy Loss
Conditional vs. Joint Probability Objectives in Language Modeling
Notational Convention for Autoregressive Conditional Probability
Modeling and Efficient Computation of Conditional Token Probabilities
A language model is generating a response sequence 'y' given an input context 'x'. The model generates the two-token sequence y = ('deep', 'learning'). The model's calculated log-probabilities for each step of the generation are as follows:
- Log-probability of the first token:
log Pr(y₁='deep' | x) = -0.7 - Log-probability of the second token, given the first:
log Pr(y₂='learning' | x, y₁='deep') = -0.4
Based on the standard method for calculating the probability of a full sequence, what is the total conditional log-likelihood of the entire sequence 'y', i.e.,
log Pr(y|x)?- Log-probability of the first token:
Comparing Model Confidence via Log-Likelihood
Analyzing a Flawed Log-Likelihood Calculation