Pith. sign in

REVIEW 9 cited by

Large Language Models on Graphs: A Comprehensive Survey

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 2312.02783 v4 pith:YANBCOK3 submitted 2023-12-05 cs.CL cs.LG

Bowen Jin , Gang Liu , Chi Han , Meng Jiang , Heng Ji , Jiawei Han This is my paper · ORCID
classification cs.CLcs.LG
keywords graphsllmslanguagemodelsscenariosabilitylargepure
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Large language models (LLMs), such as GPT4 and LLaMA, are creating significant advancements in natural language processing, due to their strong text encoding/decoding ability and newly found emergent capability (e.g., reasoning). While LLMs are mainly designed to process pure texts, there are many real-world scenarios where text data is associated with rich structure information in the form of graphs (e.g., academic networks, and e-commerce networks) or scenarios where graph data is paired with rich textual information (e.g., molecules with descriptions). Besides, although LLMs have shown their pure text-based reasoning ability, it is underexplored whether such ability can be generalized to graphs (i.e., graph-based reasoning). In this paper, we provide a systematic review of scenarios and techniques related to large language models on graphs. We first summarize potential scenarios of adopting LLMs on graphs into three categories, namely pure graphs, text-attributed graphs, and text-paired graphs. We then discuss detailed techniques for utilizing LLMs on graphs, including LLM as Predictor, LLM as Encoder, and LLM as Aligner, and compare the advantages and disadvantages of different schools of models. Furthermore, we discuss the real-world applications of such methods and summarize open-source codes and benchmark datasets. Finally, we conclude with potential future research directions in this fast-growing field. The related source can be found at https://github.com/PeterGriffinJin/Awesome-Language-Model-on-Graphs.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 9 Pith papers

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

  1. A Graph Talks, But Who's Listening? Rethinking Evaluations for Graph-Language Models

    cs.CL 2025-08 conditional novelty 6.0 of 10

    Graph-language models give no advantage over prompt-tuned LLMs on a new synthetic graph question-answering benchmark, while existing node-classification benchmarks can be solved using a single modality.

  2. Text-Attributed Graph Anomaly Detection via Multi-Scale Cross- and Uni-Modal Contrastive Learning

    cs.LG 2025-08 conditional novelty 6.0 of 10

    A joint text-graph contrastive learning framework detects anomalies in text-attributed graphs and outperforms eleven baselines across eight new datasets.

  3. Enhancing Large Language Models for Mobility Analytics with Semantic Location Tokenization

    cs.CL 2025-06 conditional novelty 6.0 of 10

    QT-Mob learns compact semantic location tokens with hierarchical vector quantization and uses multi-objective instruction tuning to improve LLM performance on next-location prediction and mobility recovery.

  4. When Do LLMs Help With Node Classification? A Comprehensive Analysis

    cs.LG 2025-02 conditional novelty 6.0 of 10

    LLM-based node classification methods give the largest gains in semi-supervised settings with few labels; their advantage over classic methods shrinks when supervision is abundant.

  5. GraphTool-Instruction: Revolutionizing Graph Reasoning in LLMs through Decomposed Subtask Instruction

    cs.LG 2024-12 conditional novelty 6.0 of 10

    Decomposing graph reasoning into graph extraction, tool name identification, and tool parameter extraction subtasks yields large accuracy gains on small LLMs and a fine-tuned 8B model that competes with GPT-4o.

  6. AIDE: Attribute-Guided MultI-Hop Data Expansion for Data Scarcity in Task-Specific Fine-tuning

    cs.CL 2024-12 conditional novelty 5.0 of 10

    AIDE generates task-relevant synthetic fine-tuning data from 10 seeds via attribute-guided multi-hop synthesis and residual connections, and reports gains over gold-data fine-tuning on several benchmarks.

  7. Inference Scaled GraphRAG: Improving Multi Hop Question Answering on Knowledge Graphs

    cs.CL 2025-06 conditional novelty 4.0 of 10

    Allowing an LLM more inference steps and majority-voted graph actions improves multi-hop knowledge-graph QA scores on GRBench.

  8. Efficient Document Retrieval with G-Retriever

    cs.LG 2025-04 conditional novelty 4.0 of 10

    Attention-based subgraph selection plus joint node-edge encoding reaches 74.20 percent test accuracy on WebQSP, a 0.41-point gain over the G-Retriever baseline.

  9. Graph2text or Graph2token: A Perspective of Large Language Models for Graph Learning

    cs.LG 2025-01 conditional novelty 4.0 of 10

    LLM-for-graph methods are divided into Graph2text and Graph2token paradigms, with four conversion challenges and a model-selection guideline.

Pith tools