KnowPath: Knowledge-enhanced Reasoning via LLM-generated Inference Paths over Knowledge Graphs

TL;DR

KnowPath enhances LLM reasoning by integrating internal knowledge with external knowledge graphs, generating interpretable inference paths for more accurate factual answers, addressing hallucination issues.

Contribution

This paper introduces KnowPath, a novel framework that effectively combines internal LLM knowledge with external knowledge graphs for improved reasoning and interpretability.

Findings

Significantly reduces hallucinations in LLM outputs

Improves reasoning accuracy on real-world datasets

Generates interpretable inference paths

Abstract

Large language models (LLMs) have demonstrated remarkable capabilities in various complex tasks, yet they still suffer from hallucinations. By incorporating and exploring external knowledge, such as knowledge graphs(KGs), LLM's ability to provide factual answers has been enhanced. This approach carries significant practical implications. However, existing methods suffer from three key limitations: insufficient mining of LLMs' internal knowledge, constrained generation of interpretable reasoning paths, and unclear fusion of internal and external knowledge. Therefore, we propose KnowPath, a knowledge-enhanced large model framework driven by the collaboration of internal and external knowledge. It relies on the internal knowledge of the LLM to guide the exploration of interpretable directed subgraphs in external knowledge graphs, better integrating the two knowledge sources for more accurate reasoning. Extensive experiments on multiple real-world datasets demonstrate the effectiveness of KnowPath. Our code and data are available at https://github.com/tize-72/KnowPath.