GRiD generates graph-like logical rules for knowledge graph reasoning by training a diffusion model with supervised pre-training on meta-graph subgraphs followed by reinforcement learning fine-tuning on rule quality metrics.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
MOTAB is a new distillation pipeline that monitors on-policy student trajectories and backtracks with teacher intervention to mitigate dual exposure biases, improving reasoning performance by about 3%.
citing papers explorer
-
Generating Graph-Like Logical Rules for Knowledge Graph Reasoning via Diffusion Models
GRiD generates graph-like logical rules for knowledge graph reasoning by training a diffusion model with supervised pre-training on meta-graph subgraphs followed by reinforcement learning fine-tuning on rule quality metrics.
-
Backtracking When It Strays: Mitigating Dual Exposure Biases in LLM Reasoning Distillation
MOTAB is a new distillation pipeline that monitors on-policy student trajectories and backtracks with teacher intervention to mitigate dual exposure biases, improving reasoning performance by about 3%.