LLaMA models encode binary sentiment most strongly in middle layers and emotions in early layers, and truncating the model at the best layer with a probe head yields efficient sentiment classifiers.
Association for Computational Linguistics
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
LLaMAs Have Feelings Too: Unveiling Sentiment and Emotion Representations in LLaMA Models Through Probing
LLaMA models encode binary sentiment most strongly in middle layers and emotions in early layers, and truncating the model at the best layer with a probe head yields efficient sentiment classifiers.