1Cademy - A language model is being trained to predict the next word in a sentence. For the input context The sun is shining..., the ideal (target) probability distribution, denoted as $Pr^t$, gives a high probability to the word brightly. The models performance is measured by a loss function that compares the models predicted probability distribution, $Pr_θ^s$, to the target distribution. Consider two different sets of model parameters, θ₁ and θ₂: - With parameters θ₁, the models distribution $Pr_{θ₁}^s$ predicts brightly with a high probability. - With parameters θ₂, the models distribution $Pr_{θ₂}^s$ predicts darkly with a high probability. Which of the following statements correctly analyzes the relationship between the parameters and the loss function for this specific input?

Learn Before

Loss Function for Conditional Probability Distributions ( $Loss(Pr^t(·|·), Pr_θ^s(·|·), x)$ )

Multiple Choice

A language model is being trained to predict the next word in a sentence. For the input context 'The sun is shining...', the ideal (target) probability distribution, denoted as $Pr^t$ , gives a high probability to the word 'brightly'. The model's performance is measured by a loss function that compares the model's predicted probability distribution, $Pr_θ^s$ , to the target distribution.

Consider two different sets of model parameters, θ₁ and θ₂:

With parameters θ₁, the model's distribution $Pr_{θ₁}^s$ predicts 'brightly' with a high probability.
With parameters θ₂, the model's distribution $Pr_{θ₂}^s$ predicts 'darkly' with a high probability.

Which of the following statements correctly analyzes the relationship between the parameters and the loss function for this specific input?

0

1

Updated 2025-09-28

Contributors are:

Who are from:

Learn Before

Related