paper-with-me

홈 › Papers

Talk like a Graph: Encoding Graphs for Large Language Models

2023-10-06 · Bahare Fatemi, Jonathan Halcrow, Bryan Perozzi

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.

📄 PDF Abstract BibTeX arXiv:2310.04560

Code (3)

ChristianaKang11/google-graphqa 공식 구현 tf
google-research/google-research/tree/master/graphqa jax
google-research/talk-like-a-graph

Tasks

Recommendation Systems

Similar Papers 제목 키워드 기반

Colorful Talks with Graphs: Human-Interpretable Graph Encodings for Large Language Models

2026-02-11 · Angelo Zangari, Peyman Baghershahi, Sourav Medya arxiv

Graph problems are fundamentally challenging for large language models (LLMs). While LLMs excel at processing unstructured text, graph tasks require reasoning over explicit structure, permutation invariance, and computat…

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

2024-02-08 · Bryan Perozzi, Bahare Fatemi, Dustin Zelle, Anton Tsitsulin 외

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, G…

Rotary Position Encodings for Graphs

2025-09-26 · Isaac Reid, Arijit Sehanobish, Cederik Höfs, Bruno Mlodozeniec 외 arxiv

We study the extent to which rotary position encodings (RoPE), a recent transformer position encoding algorithm broadly adopted in large language models (LLMs) and vision transformers (ViTs), can be applied to graph-stru…

Graph Learning

Relationship-based Neural Baby Talk

2021-03-08 · Fan Fu, TingTing Xie, Ioannis Patras, Sepehr Jalali

Understanding interactions between objects in an image is an important element for generating captions. In this paper, we propose a relationship-based neural baby talk (R-NBT) model to comprehensively investigate several…

Caption GenerationGraph Attention

Which Modality should I use -- Text, Motif, or Image? : Understanding Graphs with Large Language Models

2023-11-16 · Debarati Das, Ishaan Gupta, Jaideep Srivastava, Dongyeop Kang

Our research integrates graph data with Large Language Models (LLMs), which, despite their advancements in various fields using large text corpora, face limitations in encoding entire graphs due to context size constrain…