Concept icon
Concept

Autoregressive Dependency Guarantee in Transformer Decoders

To preserve autoregression in the Transformer decoder, the prediction generated for position ii must depend exclusively on known outputs at positions strictly less than ii. This constraint is enforced by two synchronized mechanisms: modifying the decoder's self-attention sub-layer to mask out subsequent positions, and shifting the output embeddings to the right by one position.

0

1

Concept icon
Updated 2026-09-07

Tags

Prep Sessions

Transformer Architecture and Large Language Model Capabilities @ University of Michigan - Ann Arbor

Ch.1 Transformer Architecture Fundamentals - Transformer Architecture and Large Language Model Capabilities @ University of Michigan - Ann Arbor

Decoder Masking and Autoregressive Prediction - Transformer Architecture and Large Language Model Capabilities @ University of Michigan - Ann Arbor