Intermediate layers in LLMs consistently provide stronger features than final layers across tasks and architectures, as quantified by a new framework of information-theoretic, geometric, and invariance metrics.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Layer by Layer: Uncovering Hidden Representations in Language Models
Intermediate layers in LLMs consistently provide stronger features than final layers across tasks and architectures, as quantified by a new framework of information-theoretic, geometric, and invariance metrics.