A gated Shift-FFN adapter that adds the previous token's representation to the current token's before the feedforward layer reduces repetitive looping and improves math accuracy in LoRA fine-tuned models trained on long CoT data.
Transformer Feed-Forward Layers Are Key-Value Memories
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Amplify Adjacent Token Differences: Enhancing Long Chain-of-Thought Reasoning with Shift-FFN
A gated Shift-FFN adapter that adds the previous token's representation to the current token's before the feedforward layer reduces repetitive looping and improves math accuracy in LoRA fine-tuned models trained on long CoT data.