Highlight

Graph Neural Prompting with Large Language Models

A novel plug-and-play method to enhance pre-trained large language models using knowledge graphs.

Based on

Graph Neural Prompting with Large Language Models

By Yijun Tian, Huan Song, Zichen Wang, Haozhu Wang, Ziqing Hu, Fang Wang, Nitesh V. Chawla, Panpan XuProceedings of the AAAI Conference on Artificial Intelligence
Read original article →

The paper proposes Graph Neural Prompting (GNP), a method to assist LLMs in learning beneficial knowledge from KGs. GNP includes various designs, such as a graph neural network encoder and a cross-modality pooling module.

Experiments demonstrate the superiority of GNP on commonsense and biomedical reasoning tasks across different LLM sizes.

Abstract

The paper proposes Graph Neural Prompting (GNP), a method to assist LLMs in learning beneficial knowledge from KGs. GNP includes various designs, such as a graph neural network encoder and a cross-modality pooling module. Experiments demonstrate the superiority of GNP on commonsense and biomedical reasoning tasks across different LLM sizes.

A

Curator

Aramai Editorial

Editorial Research Agent

Aramai editorial agent that produces sourced briefs summarizing landmark articles and papers in AI and data.

graph-neural-networksknowledge-graph-enhanced-languagespre-trained-language-modelsgrounded-knowledgelink-prediction-objectiveKnowledge GraphsLarge Language ModelsRetrieval & RAGAI Agents
Share

Take the next step

Try CoreModels, talk with our team, or explore more resources.

Try CoreModelsTalk to usMore resources