GaRA generates task-specific LoRA weight updates conditioned on graph structures to enable better whole-graph encoding in LLMs for zero-shot graph learning.
Title resolution pending
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4verdicts
UNVERDICTED 4representative citing papers
HyGRAG is a hierarchical graph RAG framework that constructs LLM summaries over hybrid chunk-entity graphs, retrieves via context and relation awareness across levels, and enables dynamic updates, reporting a 9.7% average accuracy gain on multi-hop reasoning tasks.
LIP decomposes GNN message passing to quantify label influences, builds a label influence graph, and propagates high-order effects to outperform prior methods on multi-label node classification benchmarks.
Learnable graph patches enable domain-agnostic pre-training of graph models by decomposing heterogeneous graphs into transferable semantic units via patch encoders and aggregators.
citing papers explorer
-
Enhancing LLMs for Graph Tasks via Graph-aware LoRA Generation
GaRA generates task-specific LoRA weight updates conditioned on graph structures to enable better whole-graph encoding in LLMs for zero-shot graph learning.
-
A Unified Framework for Context-Aware and Relation-Aware Graph Retrieval-Augmented Generation
HyGRAG is a hierarchical graph RAG framework that constructs LLM summaries over hybrid chunk-entity graphs, retrieves via context and relation awareness across levels, and enables dynamic updates, reporting a 9.7% average accuracy gain on multi-hop reasoning tasks.
-
Multi-Label Node Classification with Label Influence Propagation
LIP decomposes GNN message passing to quantify label influences, builds a label influence graph, and propagates high-order effects to outperform prior methods on multi-label node classification benchmarks.
-
Handling Feature Heterogeneity with Learnable Graph Patches
Learnable graph patches enable domain-agnostic pre-training of graph models by decomposing heterogeneous graphs into transferable semantic units via patch encoders and aggregators.