Formula

Conditional Probability in Sequence-to-Sequence Generation

In sequence-to-sequence models, the probability of generating a specific output token is conditioned on both the entire input sequence and all previously generated output tokens. This is represented by the formula Pr(yix1,...,xm,y1,...,yi1)Pr(y_i | x_1, ..., x_m, y_1, ..., y_{i-1}), where yiy_i is the current output token, (x1,...,xm)(x_1, ..., x_m) is the complete input sequence, and (y1,...,yi1)(y_1, ..., y_{i-1}) are the output tokens already generated. This conditional probability is the core calculation performed at each step of the auto-regressive generation process.

0

1

Updated 2025-10-09

Contributors are:

Who are from:

Tags

Ch.2 Generative Models - Foundations of Large Language Models

Foundations of Large Language Models

Foundations of Large Language Models Course

Computing Sciences

Related