LLM hidden states encode semantic features whose geometric relations, including axis projections, cosine similarities, low-dimensional subspaces, and steering spillovers, closely mirror human psychological associations.
Glove: Global vectors for word representation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Semantic Structure of Feature Space in Large Language Models
LLM hidden states encode semantic features whose geometric relations, including axis projections, cosine similarities, low-dimensional subspaces, and steering spillovers, closely mirror human psychological associations.