Skip to main content
← All research groups

Research group, D-21 PWr

Representation Learning Group

Representation learning in graphs, knowledge graphs and weight-space models.

  • graph neural networks
  • self-supervised graph learning
  • graph representation learning
  • knowledge graphs
  • multi-graph reasoning
  • LLMs with knowledge graphs
  • graph construction
  • graph agents
  • LLM hallucination detection
  • information theory
  • weight-space models
  • OOD detection
  • model interpretability
  • anomaly detection
  • AI4Science
7
Members
1
Recent publications

Located

D-21 PWr

Representation Learning Group develops GNNs, self-supervised graph learning, knowledge graphs, LLM-graph integration, hallucination detection, LLM analysis and models that treat neural network weights as a data modality.

Members

7 members

Recent publications

  1. FactSelfCheck: Fact-Level Black-Box Hallucination Detection for LLMs

    EACL 2026 Main Conference, 2026