A subspace-overlap score computed from frozen LLM representations and labels is proposed, with a bounding theorem in a linear setting and empirical correlations with linear probe accuracy and LoRA gains.
CARER: Contextualized affect representations for emotion recognition
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
dataset 1
citation-polarity summary
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1roles
dataset 1polarities
use dataset 1representative citing papers
citing papers explorer
-
Next Token Perception Score: Analytical Assessment of your LLM Perception Skills
A subspace-overlap score computed from frozen LLM representations and labels is proposed, with a bounding theorem in a linear setting and empirical correlations with linear probe accuracy and LoRA gains.