Pith. sign in

REVIEW 11 cited by

Talk like a Graph: Encoding Graphs for Large Language Models

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 2310.04560 v1 pith:DFDYXTYI submitted 2023-10-06 cs.LG

Bahare Fatemi , Jonathan Halcrow , Bryan Perozzi This is my paper
classification cs.LG
keywords graphgraphsreasoningencodingllmstextcomplexlanguage
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Graphs are a powerful tool for representing and analyzing complex relationships in real-world applications such as social networks, recommender systems, and computational finance. Reasoning on graphs is essential for drawing inferences about the relationships between entities in a complex system, and to identify hidden patterns and trends. Despite the remarkable progress in automated reasoning with natural text, reasoning on graphs with large language models (LLMs) remains an understudied problem. In this work, we perform the first comprehensive study of encoding graph-structured data as text for consumption by LLMs. We show that LLM performance on graph reasoning tasks varies on three fundamental levels: (1) the graph encoding method, (2) the nature of the graph task itself, and (3) interestingly, the very structure of the graph considered. These novel results provide valuable insight on strategies for encoding graphs as text. Using these insights we illustrate how the correct choice of encoders can boost performance on graph reasoning tasks inside LLMs by 4.8% to 61.8%, depending on the task.

Discussion (0). Sign in to comment.

Forward citations

Cited by 11 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. OpenAlex reports about 13 citations worldwide. Full citation record

  1. C-RE-ACT: Causal RE-ACTing Agent for O-RAN Forensic Triage

    cs.NI 2026-07 reject novelty 6.0 of 10

    An agentic O-RAN triage system that ranks root causes via SAM causal discovery and graph soft-prompting claims 89% top-3 accuracy on 140 testbed experiments.

  2. Lost in Serialization: Invariance and Generalization of LLM Graph Reasoners

    cs.LG 2025-11 conditional novelty 6.0 of 10

    Fine-tuned graph reasoners become more stable to node relabeling but more brittle to edge ordering and format, and they do not consistently beat base models on new spectral graph tasks.

  3. Modeling Code: Is Text All You Need?

    cs.AI 2025-07 conditional novelty 6.0 of 10

    A GNN-encoded LLVM IR graph, prepended as soft prompts to a frozen code LLM, improves accuracy on device mapping, algorithm classification, vulnerability detection, and code translation tasks.

  4. Enhancing LLM Agent Safety via Causal Influence Prompting

    cs.AI 2025-07 conditional novelty 6.0 of 10

    CIP, which makes LLM agents construct and refine a causal influence diagram before acting, raises refusal rates on harmful tasks in three agent-safety benchmarks.

  5. Are Large Language Models Good Temporal Graph Learners?

    cs.CL 2025-06 conditional novelty 6.0 of 10

    TGTalker prompts LLMs with the most recent edges and neighbor history of a temporal graph, achieving link prediction accuracy competitive with specialized temporal graph neural networks on five real-world datasets.

  6. Decomposing Visual Classification: Assessing Tree-Based Reasoning in VLMs

    cs.CV 2025-09 conditional novelty 5.0 of 10

    Tree-based reasoning prompts consistently underperform standard zero-shot prompting for VLM image classification on GTSRB and CIFAR-10 across three models.

  7. DGP: A Dual-Granularity Prompting Framework for Fraud Detection with Graph-Enhanced LLMs

    cs.LG 2025-07 conditional novelty 5.0 of 10

    DGP condenses neighbors into coarse-grained summaries while preserving the target node's full text, improving LLM-based fraud detection by up to 6.8 absolute AUPRC points over state-of-the-art methods.

  8. Graph Repairs with Large Language Models: An Empirical Study

    cs.CL 2025-07 conditional novelty 5.0 of 10

    Open-source LLMs can format graph repairs well and delete the violating edge, but exact-matching the intended repair is rare (up to 38%), and the validity metric used is trivially satisfied by deleting any edge.

  9. REBot: From RAG to CatRAG with Semantic Enrichment and Graph Routing

    cs.AI 2025-10 conditional novelty 4.0 of 10

    A category-routed hybrid of RAG and knowledge-graph retrieval answers Vietnamese university-regulation questions with F1 98.89% on the authors' own dataset — about 0.2 points above plain RAG.

  10. DistRAG: Towards Distance-Based Spatial Reasoning in LLMs

    cs.CL 2025-06 conditional novelty 4.0 of 10

    Retrieving distance facts from a spatial graph improves LLM answers to direct and nearest-city distance questions, while complex distance-comparison questions remain unsolved.

  11. LLMs Between the Nodes: Community Discovery Beyond Vectors

    cs.SI 2025-07 reject novelty 3.0 of 10

    CommLLM, a two-step graph-to-text plus LLM prompting method, reports high NMI on six small networks, but its evaluation omits standard community-detection baselines and relies on a prompt tuned on one test set.

Pith tools