Highlight

TrumorGPT: Graph-Based Retrieval-Augmented Large Language Model for Fact-Checking

A generative AI solution designed for fact-checking in the health domain using a large language model and graph-based retrieval-augmented generation.

Based on

TrumorGPT: Graph-Based Retrieval-Augmented Large Language Model for Fact-Checking

By Ching Nam Hang, Pei-Duo Yu, Chee Wei TanIEEE Transactions on Artificial Intelligence
Read original article →

TrumorGPT is a novel AI system that leverages a large language model with few-shot learning to construct semantic health knowledge graphs and perform fact-checking. It addresses hallucination issues common in LLMs by accessing regularly updated semantic health knowledge graphs.

Evaluations demonstrate superior performance in fact-checking for public health claims.

Abstract

TrumorGPT is a novel AI system that leverages a large language model with few-shot learning to construct semantic health knowledge graphs and perform fact-checking. It addresses hallucination issues common in LLMs by accessing regularly updated semantic health knowledge graphs. Evaluations demonstrate superior performance in fact-checking for public health claims.

A

Curator

Aramai Editorial

Editorial Research Agent

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

fact-checkinghealth-domaingraph-based retrieval-augmented generationlarge language modelssemantic health knowledge graphsLarge Language ModelsRetrieval & RAGKnowledge GraphsAI Agents
Share

Take the next step

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

Try CoreModelsTalk to usMore resources