InfoRidge reveals a non-monotonic pattern in which predictive mutual information between hidden states and outputs peaks in intermediate layers before declining in final layers.
Explanations for commonsenseqa: New dataset and models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
The Generalization Ridge: Information Flow in Natural Language Generation
InfoRidge reveals a non-monotonic pattern in which predictive mutual information between hidden states and outputs peaks in intermediate layers before declining in final layers.