Pith. sign in

REVIEW 6 cited by

GraphText: Graph Reasoning in Text Space

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 2310.01089 v1 pith:NZYPA4XH submitted 2023-10-02 cs.CL cs.LG

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

Large Language Models (LLMs) have gained the ability to assimilate human knowledge and facilitate natural language interactions with both humans and other LLMs. However, despite their impressive achievements, LLMs have not made significant advancements in the realm of graph machine learning. This limitation arises because graphs encapsulate distinct relational data, making it challenging to transform them into natural language that LLMs understand. In this paper, we bridge this gap with a novel framework, GraphText, that translates graphs into natural language. GraphText derives a graph-syntax tree for each graph that encapsulates both the node attributes and inter-node relationships. Traversal of the tree yields a graph text sequence, which is then processed by an LLM to treat graph tasks as text generation tasks. Notably, GraphText offers multiple advantages. It introduces training-free graph reasoning: even without training on graph data, GraphText with ChatGPT can achieve on par with, or even surpassing, the performance of supervised-trained graph neural networks through in-context learning (ICL). Furthermore, GraphText paves the way for interactive graph reasoning, allowing both humans and LLMs to communicate with the model seamlessly using natural language. These capabilities underscore the vast, yet-to-be-explored potential of LLMs in the domain of graph machine learning.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 6 Pith papers

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

  1. Agentic Graph Token Reasoning

    cs.LG 2026-08 conditional novelty 7.0 of 10

    Agentic Graph Token (AGT) reasoning lets an LLM iteratively select graph views, encode them as tokens, and reason step-by-step, beating static graph-token and text-agent baselines on seven graph domains.

  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. Court of LLMs: Evidence-Augmented Generation via Multi-LLM Collaboration for Text-Attributed Graph Anomaly Detection

    cs.LG 2025-08 conditional novelty 6.0 of 10

    CoLL uses two specialized LLM 'prosecutors' and an LLM 'judge' to generate textual anomaly evidence, which a gated GNN then fuses with graph structure for state-of-the-art text-attributed graph anomaly detection.

  4. Quantizing Text-attributed Graphs for Semantic-Structural Integration

    cs.LG 2025-07 conditional novelty 6.0 of 10

    STAG quantizes fused graph-structure and text embeddings into discrete tokens from a frozen LLM vocabulary, enabling competitive few-shot and zero-shot node classification with or without an LLM.

  5. 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.

  6. Matching Game Preferences Through Dialogical Large Language Models: A Perspective

    cs.AI 2025-07 conditional novelty 4.0 of 10

    This perspective paper proposes the D-LLM framework, which couples the authors' GRAPHYP knowledge graphs with LLMs to personalize AI responses and make reasoning traceable, but no empirical validation is presented.

Pith tools