Large Language Model-Enhanced Symbolic Reasoning for Knowledge Base Completion

TL;DR

This paper introduces a novel framework that combines large language models with rule-based reasoning to improve knowledge base completion, leveraging LLMs for diverse rule generation and a rule reasoner for refinement, achieving robust results.

Contribution

The paper presents a new framework integrating LLMs with rule-based reasoning for KB completion, enhancing rule diversity and reliability over traditional methods.

Findings

Effective rule proposals from LLMs improve KB completion.

Refined rules reduce hallucinations and increase accuracy.

Framework demonstrates strong performance across datasets.

Abstract

Integrating large language models (LLMs) with rule-based reasoning offers a powerful solution for improving the flexibility and reliability of Knowledge Base Completion (KBC). Traditional rule-based KBC methods offer verifiable reasoning yet lack flexibility, while LLMs provide strong semantic understanding yet suffer from hallucinations. With the aim of combining LLMs' understanding capability with the logical and rigor of rule-based approaches, we propose a novel framework consisting of a Subgraph Extractor, an LLM Proposer, and a Rule Reasoner. The Subgraph Extractor first samples subgraphs from the KB. Then, the LLM uses these subgraphs to propose diverse and meaningful rules that are helpful for inferring missing facts. To effectively avoid hallucination in LLMs' generations, these proposed rules are further refined by a Rule Reasoner to pinpoint the most significant rules in the KB for Knowledge Base Completion. Our approach offers several key benefits: the utilization of LLMs to enhance the richness and diversity of the proposed rules and the integration with rule-based reasoning to improve reliability. Our method also demonstrates strong performance across diverse KB datasets, highlighting the robustness and generalizability of the proposed framework.