LLMs compress concreteness into a consistent 1D direction in mid-to-late layers that separates literal from figurative noun uses and supports efficient classification plus steering.
A Robustly Optimized BERT Pre-training Approach with Post-training
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CL 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Compares supervised architectures for political text scaling to evaluate joint prediction benefits and classification-regression middle grounds.
citing papers explorer
-
Exploring Concreteness Through a Figurative Lens
LLMs compress concreteness into a consistent 1D direction in mid-to-late layers that separates literal from figurative noun uses and supports efficient classification plus steering.
-
Comparing Architectures for Supervised Political Scaling
Compares supervised architectures for political text scaling to evaluate joint prediction benefits and classification-regression middle grounds.