Activity (Process)

Final Reward Score Calculation in RLHF

Once a comprehensive vector representation of the concatenated input sequence is obtained from the Transformer layer stack, a final output layer, such as a linear transformation layer, is built directly on top of this representation. This layer translates the vector into a final scalar reward score, denoted by R(seqk)R(\mathrm{seq}_k) or R(x,yk)R(\mathbf{x},\mathbf{y}_k), representing the evaluation for the given prompt x\mathbf{x} and output yk\mathbf{y}_k.

0

1

Updated 2026-04-20

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