Crossed random-effects models on LLM word ratings show 16.9% variance from genuine stimulus-specific individuality, exceeding null models and forming coherent per-model fingerprints.
Crutch, and Jamie Reilly
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
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.
citing papers explorer
-
Machine individuality: Separating genuine idiosyncrasy from response bias in large language models
Crossed random-effects models on LLM word ratings show 16.9% variance from genuine stimulus-specific individuality, exceeding null models and forming coherent per-model fingerprints.
-
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.