PromptGNN-sim uses GAT-based semantically aware neighborhood selection and structure-aware LLM prompts with bi-directional contrastive alignment to outperform prior GNN, LLM, and fusion methods on text-attributed graph datasets.
hub
Llaga: Large language and graph assistant
17 Pith papers cite this work. Polarity classification is still indexing.
17
Pith papers citing it
hub tools
citation-role summary
background 3
citation-polarity summary
roles
background 3polarities
background 3representative citing papers
Mechanistic analysis of GLMs shows graph sink tokens have high activation but low importance for predictions, indicating decoupling between saliency and graph-semantic utility.
GoR extracts citation DAGs using position, frequency, predecessor links and time, then fine-tunes Qwen2.5-7B on 498 seed papers to generate ideas, claiming SOTA over gpt-4o baselines via LLM judges.
DyGFM introduces decoupled pre-training and divergence-conditioned prompts to create the first multi-domain dynamic graph foundation model that outperforms baselines on node classification and link prediction.
GraphSSR introduces an adaptive SSR pipeline with SSR-SFT data synthesis and SSR-RL (Authenticity-Reinforced and Denoising-Reinforced stages) to overcome one-size-fits-all subgraph noise in zero-shot LLM graph reasoning.
GraphScout trains LLMs to autonomously synthesize structured training data from knowledge graphs via flexible exploration tools, enabling a 4B model to outperform larger LLMs by 16.7% on average with fewer inference tokens and strong cross-domain transfer.
GraspLLM extracts dataset-agnostic structural patterns via motif contrastive learning and aligns contextual subgraphs to LLM tokens, outperforming prior LLM-based methods on TAGs especially in zero-shot settings.
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.
HyRAG improves zero-shot generalization of graph foundation models by indexing and retrieving from tree-structured knowledge in hyperbolic space via multi-granularity retrieval and dual-path fusion.
S2Aligner decouples semantic and structural components in LLM-as-Aligner pre-training for sparse TAGs and uses structure-oriented reconstruction plus domain risk balancing to improve transferability and reduce generalization gaps.
GTLM injects graph-aware attention biases into LLMs using only 0.015% extra parameters, enabling native graph processing that matches 7B models with a 1B model on text-attributed graph benchmarks.
DuConTE is a dual-granularity text encoder that incorporates graph topology into language model attention for improved node representations in text-attributed graphs.
A structured survey organizing graph-LLM integration methods by purpose, modality, and strategy across application domains.
GEMS formulates close-ended human-behavior simulation as link prediction on a heterogeneous graph and matches or exceeds LLM performance with three orders of magnitude fewer parameters across three datasets and three evaluation settings.
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.
A survey proposing a holistic GraphRAG framework with components including query processor, retriever, organizer, generator, and data source, plus domain-tailored reviews, challenges, and future directions.
citing papers explorer
-
PromptGNN-sim: Deep Fusion and Alignment of GNN and LLMs for Text-Attributed Graph Learning
PromptGNN-sim uses GAT-based semantically aware neighborhood selection and structure-aware LLM prompts with bi-directional contrastive alignment to outperform prior GNN, LLM, and fusion methods on text-attributed graph datasets.
-
When Graph Tokens Sink: A Mechanistic Analysis of Graph Language Models
Mechanistic analysis of GLMs shows graph sink tokens have high activation but low importance for predictions, indicating decoupling between saliency and graph-semantic utility.
-
Graphs of Research: Citation Evolution Graphs as Supervision for Research Idea Generation
GoR extracts citation DAGs using position, frequency, predecessor links and time, then fine-tunes Qwen2.5-7B on 498 seed papers to generate ideas, claiming SOTA over gpt-4o baselines via LLM judges.
-
Decoupled and Divergence-Conditioned Prompt for Multi-domain Dynamic Graph Foundation Models
DyGFM introduces decoupled pre-training and divergence-conditioned prompts to create the first multi-domain dynamic graph foundation model that outperforms baselines on node classification and link prediction.
-
Beyond One-Size-Fits-All: Adaptive Subgraph Denoising for Zero-Shot Graph Learning with Large Language Models
GraphSSR introduces an adaptive SSR pipeline with SSR-SFT data synthesis and SSR-RL (Authenticity-Reinforced and Denoising-Reinforced stages) to overcome one-size-fits-all subgraph noise in zero-shot LLM graph reasoning.
-
GraphScout: Empowering Large Language Models with Intrinsic Exploration Ability for Agentic Graph Reasoning
GraphScout trains LLMs to autonomously synthesize structured training data from knowledge graphs via flexible exploration tools, enabling a 4B model to outperform larger LLMs by 16.7% on average with fewer inference tokens and strong cross-domain transfer.
-
GraspLLM: Towards Zero-Shot Generalization on Text-Attributed Graphs with LLMs
GraspLLM extracts dataset-agnostic structural patterns via motif contrastive learning and aligns contextual subgraphs to LLM tokens, outperforming prior LLM-based methods on TAGs especially in zero-shot settings.
-
Beyond the Golden Teacher: Enhancing Graph Learning through LLM-GNN Co-teaching
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.
-
Generalizing Graph Foundation Models via Hyperbolic Retrieval-Augmented Generation
HyRAG improves zero-shot generalization of graph foundation models by indexing and retrieving from tree-structured knowledge in hyperbolic space via multi-granularity retrieval and dual-path fusion.
-
S2Aligner: Pair-Efficient and Transferable Pre-Training for Sparse Text-Attributed Graphs
S2Aligner decouples semantic and structural components in LLM-as-Aligner pre-training for sparse TAGs and uses structure-oriented reconstruction plus domain risk balancing to improve transferability and reduce generalization gaps.
-
Teaching LLMs to See Graphs: Unifying Text and Structural Reasoning
GTLM injects graph-aware attention biases into LLMs using only 0.015% extra parameters, enabling native graph processing that matches 7B models with a 1B model on text-attributed graph benchmarks.
-
DuConTE: Dual-Granularity Text Encoder with Topology-Constrained Attention for Text-attributed Graphs
DuConTE is a dual-granularity text encoder that incorporates graph topology into language model attention for improved node representations in text-attributed graphs.
-
Integrating Graphs, Large Language Models, and Agents: Reasoning and Retrieval
A structured survey organizing graph-LLM integration methods by purpose, modality, and strategy across application domains.
-
Graph-Based Alternatives to LLMs for Human Simulation
GEMS formulates close-ended human-behavior simulation as link prediction on a heterogeneous graph and matches or exceeds LLM performance with three orders of magnitude fewer parameters across three datasets and three evaluation settings.
-
AGE: Adaptive-masking for Graph Embedding in Graph Retrieval-Augmented Generation
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: Graph and LLM Joint Pretraining for Graph-Level Tasks
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.
-
Retrieval-Augmented Generation with Graphs (GraphRAG)
A survey proposing a holistic GraphRAG framework with components including query processor, retriever, organizer, generator, and data source, plus domain-tailored reviews, challenges, and future directions.