LLMs represent semantic relations geometrically via embedding distance and direction; a linear Polar Probe decodes these structures from middle-layer activations and generalizes to new entities.
Nature , volume=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
NEO induces compositional latent programs as world theories from observations and executes them to enable explanation-driven generalization.
citing papers explorer
-
Polar probe linearly decodes semantic structures from LLMs
LLMs represent semantic relations geometrically via embedding distance and direction; a linear Polar Probe decodes these structures from middle-layer activations and generalizes to new entities.
-
Learning to Theorize the World from Observation
NEO induces compositional latent programs as world theories from observations and executes them to enable explanation-driven generalization.