Path Pooling: Training-Free Structure Enhancement for Efficient Knowledge Graph Retrieval-Augmented Generation
This addresses the issue of hallucinations and knowledge deficiencies in LLMs for real-world applications, offering an incremental improvement to existing KG-RAG methods.
The paper tackles the problem of effectively incorporating structure information in knowledge graph-based retrieval-augmented generation (KG-RAG) for large language models, proposing path pooling to enhance performance with negligible cost, achieving consistent improvements across various settings.
Although Large Language Models achieve strong success in many tasks, they still suffer from hallucinations and knowledge deficiencies in real-world applications. Many knowledge graph-based retrieval-augmented generation (KG-RAG) methods enhance the quality and credibility of LLMs by leveraging structure and semantic information in KGs as external knowledge bases. However, these methods struggle to effectively incorporate structure information, either incurring high computational costs or underutilizing available knowledge. Inspired by smoothing operations in graph representation learning, we propose path pooling, a simple, training-free strategy that introduces structure information through a novel path-centric pooling operation. It seamlessly integrates into existing KG-RAG methods in a plug-and-play manner, enabling richer structure information utilization. Extensive experiments demonstrate that incorporating the path pooling into the state-of-the-art KG-RAG method consistently improves performance across various settings while introducing negligible additional cost.