Pith. sign in

REVIEW 5 cited by

GraphGPT: Graph Instruction Tuning for Large Language Models

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2310.13023 v3 pith:R7CG4OJM submitted 2023-10-19 cs.CL cs.AI

classification cs.CLcs.AI
keywords graphgraphgptdataframeworkgeneralizationinstructionlearningllms
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Graph Neural Networks (GNNs) have evolved to understand graph structures through recursive exchanges and aggregations among nodes. To enhance robustness, self-supervised learning (SSL) has become a vital tool for data augmentation. Traditional methods often depend on fine-tuning with task-specific labels, limiting their effectiveness when labeled data is scarce. Our research tackles this by advancing graph model generalization in zero-shot learning environments. Inspired by the success of large language models (LLMs), we aim to create a graph-oriented LLM capable of exceptional generalization across various datasets and tasks without relying on downstream graph data. We introduce the GraphGPT framework, which integrates LLMs with graph structural knowledge through graph instruction tuning. This framework includes a text-graph grounding component to link textual and graph structures and a dual-stage instruction tuning approach with a lightweight graph-text alignment projector. These innovations allow LLMs to comprehend complex graph structures and enhance adaptability across diverse datasets and tasks. Our framework demonstrates superior generalization in both supervised and zero-shot graph learning tasks, surpassing existing benchmarks. The open-sourced model implementation of our GraphGPT is available at https://github.com/HKUDS/GraphGPT.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. One Model, Many Graphs: Learning over Attributed Graphs across Heterogeneous Modalities with Vision-Language Models

    cs.LG 2026-07 conditional novelty 6.0 of 10

    OMG-VLM is a single VLM-based model that handles text-, image-, and multi-attributed graphs through structure-aware adapters, reporting gains on several node/link prediction benchmarks.

  2. Harnessing Adaptive Topology Representations for Zero-Shot Graph Question Answering

    cs.CL 2025-08 conditional novelty 6.0 of 10

    DynamicTRF learns question-level preferences over eight graph representations and routes each query to the best one, improving zero-shot graph QA accuracy and output brevity on seven algorithmic and two downstream tasks.

  3. GraphLAMA: Enabling Efficient Adaptation of Graph Language Models with Limited Annotations

    cs.CL 2025-06 conditional novelty 6.0 of 10

    A frozen-LLM graph model with a small tuned adapter (about 726k parameters, 3MB) outperforms in-context learning and instruction-tuned graph LLMs in few/zero-shot node classification and summary generation.

  4. MLaGA: Multimodal Large Language and Graph Assistant

    cs.AI 2025-06 conditional novelty 6.0 of 10

    MLaGA extends LLM-based graph reasoning from text-only graphs to multimodal graphs with image and text node attributes via a structure-aware aligner and multimodal instruction tuning.

  5. LKD-KGC: Domain-Specific KG Construction via LLM-driven Knowledge Dependency Parsing

    cs.CL 2025-05 conditional novelty 6.0 of 10

    An LLM pipeline that orders documents by knowledge dependency, builds an entity schema from summaries, and extracts triples beats prior unsupervised KG construction baselines on three domain corpora.

Pith tools