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

2024-06-03

AI Summary

To address hallucination and imprecise reasoning chains in large language models (LLMs) for knowledge graph question answering (KGQA), this paper proposes a collaborative dual-path reasoning framework that synergistically integrates explicit, structured reasoning via a graph neural network (GNN) and implicit, intuitive reasoning via a frozen LLM. Grounded in dual-process cognitive theory, the GNN actively extracts high-quality reasoning paths, while the LLM performs lightweight decision-making only. We introduce an LLM-augmented GNN training mechanism and a knowledge-enhanced multiple-choice prompting paradigm to enable reasoning-chain distillation and controllable guidance. Evaluated on three KGQA benchmarks, our method achieves state-of-the-art performance, significantly improves inference efficiency, and generates interpretable, high-accuracy intermediate reasoning chains—thereby jointly enhancing accuracy, efficiency, and transparency.

Technology Category

• Knowledge Representation and Reasoning: Knowledge Acquisition
• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Question Answering

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG

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.

Problem

• Enhance LLMs' reasoning with explicit knowledge from KGs.
• Integrate GNN for explicit reasoning to complement LLMs' implicit reasoning.
• Improve KGQA performance with efficient, interpretable reasoning chains.

Innovation

• Integrates GNN for explicit KG reasoning
• LLM-empowered GNN extracts high-quality reasoning chains
• Refines chains into knowledge-enhanced prompts for LLM