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.
A Review of Relational Machine Learning for Knowledge Graphs
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
Empirical comparison shows gradient-based explanations for GNN node similarities are actionable, consistent, and retain effects when sparsified, unlike mutual information explanations.
BioBLP is a modular embedding framework for multimodal biomedical KGs supporting heterogeneous attributes and missing data, with a pretraining strategy that improves results on drug-protein interaction prediction especially for low-degree entities.
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.
-
Explaining Graph Neural Networks for Node Similarity on Graphs
Empirical comparison shows gradient-based explanations for GNN node similarities are actionable, consistent, and retain effects when sparsified, unlike mutual information explanations.
-
BioBLP: A Modular Framework for Learning on Multimodal Biomedical Knowledge Graphs
BioBLP is a modular embedding framework for multimodal biomedical KGs supporting heterogeneous attributes and missing data, with a pretraining strategy that improves results on drug-protein interaction prediction especially for low-degree entities.