KREPE applies masked discrete diffusion to unify link prediction and fact generation on hyper-relational knowledge graphs, claiming SOTA results and superiority over LLM baselines.
Enhancing large language model for knowledge graph completion via structure-aware alignment-tuning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Generative Representation Learning on Hyper-relational Knowledge Graphs via Masked Discrete Diffusion
KREPE applies masked discrete diffusion to unify link prediction and fact generation on hyper-relational knowledge graphs, claiming SOTA results and superiority over LLM baselines.