Activity (Process)

Generating Predictions with Augmented Input in RAG

In the final stage of the Retrieval-Augmented Generation (RAG) process, the augmented input, denoted as x\mathbf{x}', serves as the context. The Large Language Model then uses this combined information to predict the subsequent text, an operation that is mathematically represented by the conditional probability model Pr(yx)\Pr(\mathbf{y}|\mathbf{x}').

0

1

Updated 2026-04-23

Contributors are:

Who are from:

Tags

Ch.3 Prompting - Foundations of Large Language Models

Foundations of Large Language Models

Foundations of Large Language Models Course

Computing Sciences

Ch.2 Generative Models - Foundations of Large Language Models