Dual Reasoning: A GNN-LLM Collaborative Framework for Knowledge Graph Question Answering

TL;DR

This paper introduces DualR, a framework combining GNNs and LLMs to improve knowledge graph question answering by explicitly reasoning on KGs and guiding LLMs with refined reasoning chains, achieving state-of-the-art results.

Contribution

The paper presents a novel dual-process framework integrating GNN-based explicit reasoning with LLMs, enhancing KGQA performance and interpretability.

Findings

DualR achieves state-of-the-art accuracy on benchmark datasets.

The framework improves reasoning efficiency and interpretability.

Explicit reasoning chains effectively guide LLMs to accurate answers.

Abstract

Large Language Models (LLMs) excel at intuitive, implicit reasoning. Guiding LLMs to construct thought chains can enhance their deliberate reasoning abilities, but also faces challenges such as hallucination. Knowledge Graphs (KGs) can provide explicit structured knowledge for LLMs to alleviate these issues. However, existing KG-enhanced methods often overlook explicit graph learning, making it challenging to efficiently provide precise reasoning chains for LLMs. Following dual-process theory, we propose Dual-Reasoning (DualR), a novel framework that integrates an external system based on Graph Neural Network (GNN) for explicit reasoning on KGs, complementing the implicit reasoning of LLMs through externalized reasoning chains. DualR designs an LLM-empowered GNN module for explicit learning on KGs, efficiently extracting high-quality reasoning chains. These reasoning chains are then refined to a knowledge-enhanced multiple-choice prompt, guiding a frozen LLM to reason thoughtfully for final answer determination. Extensive experiments on three benchmark KGQA datasets demonstrate that DualR achieves state-of-the-art performance while maintaining high efficiency and interpretability.