Sim Cot Supervised Implicit Chain Of Thought

Train LLMs to reason implicitly with step-level supervision, stabilizing latent representations while preserving 2.3× inference speedup over explicit chain-of-thought. Addresses training collapse in implicit reasoning by aligning intermediate latent states with explicit reasoning steps through an auxiliary decoder during training, then removing the decoder for efficient inference.

adu2021 Updated 7 repo stars

File contents

adu2021/skillxiv commit 05c799a4bd

Frequently asked questions

npx get-skill add adu2021/sim-cot-supervised-implicit-chain-of-thought