Rotary embeddings create bandwidth-dependent attention decay during graph linearization; GaLA corrects this at inference time to boost performance on text-attributed graphs.
Graphtext: Graph rea- soning in text space.arXiv preprint arXiv:2310.01089
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
years
2026 5representative citing papers
ALL-IN projects node features to a random shared space and uses covariance operators to produce representations invariant to input feature permutations and orthogonal transformations, enabling transfer across graph datasets.
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.
AgentGL is an RL-driven LLM agent framework for agentic graph learning that uses graph-native tools and curriculum training to outperform GraphLLM and GraphRAG baselines by up to 17.5% on node classification and 28.4% on link prediction across text-attributed graph benchmarks.
citing papers explorer
-
Formalizing and Mitigating Structural Distortion in LLM Attention for Graph Reasoning
Rotary embeddings create bandwidth-dependent attention decay during graph linearization; GaLA corrects this at inference time to boost performance on text-attributed graphs.
-
Bridging Input Feature Spaces Towards Graph Foundation Models
ALL-IN projects node features to a random shared space and uses covariance operators to produce representations invariant to input feature permutations and orthogonal transformations, enabling transfer across graph datasets.
-
Revisiting Graph-Tokenizing Large Language Models: A Systematic Evaluation of Graph Token Understanding
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.
-
AgentGL: Towards Agentic Graph Learning with LLMs via Reinforcement Learning
AgentGL is an RL-driven LLM agent framework for agentic graph learning that uses graph-native tools and curriculum training to outperform GraphLLM and GraphRAG baselines by up to 17.5% on node classification and 28.4% on link prediction across text-attributed graph benchmarks.
- GraphReview: Scientific Paper Evaluation via LLM-based Graph Evidence Expansion