Generate-on-Graph: Treat LLM as both Agent and KG in Incomplete Knowledge Graph Question Answering

arXiv:2404.14741v1 Announce Type: new
Abstract: To address the issue of insufficient knowledge and the tendency to generate hallucination in Large Language Models (LLMs), numerous studies have endeavored to integrate LLMs with Knowledge Graphs (KGs). However, all these methods are evaluated on conventional Knowledge Graph Question Answering (KGQA) with complete KGs, where the factual triples involved in each question are entirely covered by the given KG. In this situation, LLM mainly acts as an agent to find answer entities by exploring …

abstract agent arxiv cs.ai cs.cl generate graph graphs hallucination however issue knowledge knowledge graph knowledge graphs language language models large language large language models llm llms question question answering studies type