提出无需训练的路径池化，提升知识图谱增强生成的效果
Path Pooling: Training-Free Structure Enhancement for Efficient Knowledge Graph Retrieval-Augmented Generation
- 通过路径中心池化引入结构信息，无需额外训练
- 在多个设置下显著提升现有KG-RAG方法性能
- 可无缝集成到现有系统，开销极小，适合部署
尽管大语言模型在诸多任务中表现优异，但在实际应用中仍存在幻觉和知识不足问题。基于知识图谱的检索增强生成（KG-RAG）方法通过利用知识图谱中的结构与语义信息作为外部知识库，提升了大模型的质量与可信度。然而，现有方法难以有效融合结构信息，或计算成本过高，或未充分利用已有知识。受图表示学习中平滑操作的启发，我们提出路径池化（Path Pooling），一种简单、无需训练的策略，通过新颖的路径中心池化操作引入结构信息。该方法可无痛集成至现有KG-RAG方法中，实现即插即用，显著提升结构信息利用率。大量实验表明，将路径池化应用于最先进的KG-RAG方法，在多种场景下均能持续提升性能，且额外开销可忽略不计。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。