Path Pooling: Training-Free Structure Enhancement for Efficient Knowledge Graph Retrieval-Augmented Generation

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Wang, Hairu, Feng, Yuan, Xie, Xike, Zhou, S Kevin
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916761200230400
author Wang, Hairu
Feng, Yuan
Xie, Xike
Zhou, S Kevin
author_facet Wang, Hairu
Feng, Yuan
Xie, Xike
Zhou, S Kevin
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2503_05203
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Path Pooling: Training-Free Structure Enhancement for Efficient Knowledge Graph Retrieval-Augmented Generation
Wang, Hairu
Feng, Yuan
Xie, Xike
Zhou, S Kevin
Artificial Intelligence
Computation and Language
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.
title Path Pooling: Training-Free Structure Enhancement for Efficient Knowledge Graph Retrieval-Augmented Generation
topic Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2503.05203