pith. sign in

Translating embeddings for modeling multi-relational data , year =

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

fields

cs.AI 1 cs.CL 1

years

2026 2

verdicts

UNVERDICTED 2

representative citing papers

Polar probe linearly decodes semantic structures from LLMs

cs.CL · 2026-05-13 · unverdicted · novelty 6.0 · 2 refs

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.

citing papers explorer

Showing 2 of 2 citing papers.