Pith. sign in

REVIEW 13 cited by

Let Your Graph Do the Talking: Encoding Structured Data for LLMs

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 2402.05862 v1 pith:JGZD5L3Z submitted 2024-02-08 cs.LG cs.AIcs.SIstat.ML

Bryan Perozzi , Bahare Fatemi , Dustin Zelle , Anton Tsitsulin , Mehran Kazemi , Rami Al-Rfou , Jonathan Halcrow This is my paper · ORCID
classification cs.LGcs.AIcs.SIstat.ML
keywords structureddatagraphencodingllmstasksworkexplicitly
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

How can we best encode structured data into sequential form for use in large language models (LLMs)? In this work, we introduce a parameter-efficient method to explicitly represent structured data for LLMs. Our method, GraphToken, learns an encoding function to extend prompts with explicit structured information. Unlike other work which focuses on limited domains (e.g. knowledge graph representation), our work is the first effort focused on the general encoding of structured data to be used for various reasoning tasks. We show that explicitly representing the graph structure allows significant improvements to graph reasoning tasks. Specifically, we see across the board improvements - up to 73% points - on node, edge and, graph-level tasks from the GraphQA benchmark.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 13 Pith papers

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

  1. GARDRec: Decision-Level Graph Grounding for Large Language Model Recommendation

    cs.IR 2026-08 conditional novelty 6.0 of 10

    GARDRec improves LLM-based next-item ranking by grounding decisions in knowledge-graph embeddings, personalized graph contexts, and late-stage scoring rather than prompt text.

  2. 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.

  3. KoRe: Compact Knowledge Representations for Large Language Models

    cs.CL 2026-05 unverdicted novelty 6.0 of 10

    KoRe encodes 1-hop knowledge graph subgraphs as compact discrete tokens for injection into LLMs, achieving competitive benchmark performance with up to 10x token reduction.

  4. 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.

  5. 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.

  6. 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.

  7. Generalizable LLM Learning of Graph Synthetic Data with Post-training Alignment

    cs.LG 2025-06 conditional novelty 6.0 of 10

    Post-training alignment on synthetic graph data yields statistically significant gains on some real-world implicit-graph tasks, but gains are inconsistent and multi-step reasoning remains fragile.

  8. G1: Teaching LLMs to Reason on Graphs with Reinforcement Learning

    cs.LG 2025-05 conditional novelty 6.0 of 10

    Reinforcement learning on synthetic graph-theoretic tasks sharply improves LLM graph reasoning, transferring to larger graphs, new encodings, and real-world tasks.

  9. Efficiently Learning Branching Networks for Multitask Algorithmic Reasoning

    cs.LG 2025-11 conditional novelty 5.0 of 10

    AutoBRANE learns tree-structured branching networks for multitask algorithmic reasoning via gradient-based task affinities and convex relaxation.

  10. Graph-Based Physics-Guided Urban PM2.5 Air Quality Imputation with Constrained Monitoring Data

    cs.LG 2025-06 conditional novelty 5.0 of 10

    GraPhy, a physics-inspired graph neural network with wind-based edge features and learnable diffusion scaling, reports the best PM2.5 imputation accuracy among six baselines on 41 sensors in Fresno, California.

  11. Walk&Retrieve: Simple Yet Effective Zero-shot Retrieval-Augmented Generation via Knowledge Graph Walks

    cs.IR 2025-05 conditional novelty 5.0 of 10

    Offline walks over a knowledge graph, verbalized into text and retrieved by embedding similarity, let a single LLM call answer multi-hop questions competitively without any fine-tuning.

  12. Spectral Journey: How Transformers Predict the Shortest Path

    cs.LG 2025-02 conditional novelty 5.0 of 10

    Two-layer transformers learn shortest paths on small graphs by building embeddings that correlate with spectral decomposition of the line graph, yielding an approximate spectral path-finding algorithm.

  13. Efficient Graph Understanding with LLMs via Structured Context Injection

    cs.AI 2025-08 conditional novelty 4.0 of 10

    Giving LLMs graph inputs whose nodes are named after Game of Thrones characters, with relationship weights, raises accuracy on four graph-reasoning tasks using a single prompt.

Pith tools