Bidirectional LLM-GNN co-teaching with round-based pseudo-label preference optimization outperforms golden-teacher baselines on few-shot TAG benchmarks by 3-8% absolute gains.
Can llms effectively leverage graph structural information: when and why
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 8roles
background 1polarities
background 1representative citing papers
KCoT reframes CoT graph learning as k-means clustering by establishing a formal correspondence between Transformer blocks and k-means assignment/update steps, with a Semantic Discriminating Prompt and structure alignment yielding gains on benchmarks.
GTokenLLMs do not fully understand graph tokens, exhibiting over-sensitivity or insensitivity to instruction changes and relying heavily on text for reasoning even when graph information is preserved.
AGE applies adaptive masking via a learnable sampler in Transformer-based SSL to align graph and text embeddings, yielding higher accuracy on four GraphQA benchmarks for non-parametric GraphRAG.
GLIP is a joint GNN-LLM pretraining framework that uses augmentation, multi-token selection, a diffusion projector, and combined contrastive plus semantic losses to boost graph classification and reasoning after fine-tuning on limited labels.
Keyword-enhanced classification performs best among zero-shot variants; knowledge graph augmentation improves small models but degrades large ones, while self-consistency adds cost without benefit.
STK-Adapter adds Spatial-Temporal MoE, Event-Aware MoE, and Cross-Modality Alignment MoE to integrate evolving TKG graphs and event chains into LLMs, reducing information loss and improving extrapolation performance over prior methods.
G-Defense builds claim-centered graphs from sub-claims, applies RAG for evidence and competing explanations, then uses graph inference to detect fake news veracity and generate intuitive explanation graphs, claiming SOTA results.
citing papers explorer
-
A Graph-Enhanced Defense Framework for Explainable Fake News Detection with LLM
G-Defense builds claim-centered graphs from sub-claims, applies RAG for evidence and competing explanations, then uses graph inference to detect fake news veracity and generate intuitive explanation graphs, claiming SOTA results.