Layer Cake Contrastive Decoding

Improve factual accuracy in LLM generation through decoding-time layer-wise attention suppression. Selectively suppress attention to specific token types at their most influential transformer depths without training or model modifications. Use when you need to reduce hallucinations and improve factual correctness at inference time.

adu2021 Updated 7 repo stars

File contents

adu2021/skillxiv commit 15480ce0b3

Frequently asked questions

npx get-skill add adu2021/layer-cake-contrastive-decoding