SG-RAG MOT: SubGraph Retrieval Augmented Generation with Merging and Ordering Triplets for Knowledge Graph Multi-Hop Question Answering

Large language models (LLMs) often tend to hallucinate, especially in domain-specific tasks and tasks that require reasoning. Previously, we introduced SubGraph Retrieval Augmented Generation (SG-RAG) as a novel Graph RAG method for multi-hop question answering. SG-RAG leverages Cypher queries to se...

Ausführliche Beschreibung

Bibliografische Detailangaben

Hauptverfasser:	Ahmmad O. M. Saleh, Gokhan Tur, Yucel Saygin
Format:	Artigo
Sprache:	Inglês
Veröffentlicht:	MDPI AG 2025-08-01
Schriftenreihe:	Machine Learning and Knowledge Extraction
Schlagworte:	large language model knowledge graph question answering multi-hop question graph RAG
Online-Zugang:	https://www.mdpi.com/2504-4990/7/3/74
Tags:	Tag hinzufügen Keine Tags, Fügen Sie das erste Tag hinzu!