基于拓扑的不完整知识图谱推理与图基软提示
Topology-Aware Reasoning over Incomplete Knowledge Graph with Graph-Based Soft Prompting
AI总结：
本文提出基于图的软提示框架，通过图神经网络编码子图生成软提示，使LLM在更丰富的结构上下文中推理，减少缺失边的影响，提升多跳KBQA性能。
摘要：
大型语言模型（LLMs）在各种任务中表现出色，但在知识密集型场景中容易产生幻觉。知识库问答（KBQA）通过在知识图谱（KGs）上进行生成来缓解这一问题。然而，大多数多跳KBQA方法依赖于显式的边遍历，使其对KG不完整敏感。在本文中，我们提出了一种新颖的基于图的软提示框架，将推理范式从节点级路径遍历转向子图级推理。具体来说，我们使用图神经网络（GNN）将提取的结构子图编码为软提示，使LLM能够在更丰富的结构上下文中推理，并识别超出直接图邻居的相关实体，从而减少对缺失边的敏感性。此外，我们引入了双阶段范式，以减少计算成本同时保持良好的性能：轻量级LLM首先利用软提示识别问题相关实体和关系，随后更强大的LLM用于证据感知的答案生成。在四个多跳KBQA基准测试中，我们的方法在三个基准上实现了最先进的性能，证明了其有效性。代码可在仓库：https://github.com/Wangshuaiia/GraSP中获得。
英文摘要：
Large Language Models (LLMs) have shown remarkable capabilities across various tasks but remain prone to hallucinations in knowledge-intensive scenarios. Knowledge Base Question Answering (KBQA) mitigates this by grounding generation in Knowledge Graphs (KGs). However, most multi-hop KBQA methods rely on explicit edge traversal, making them fragile to KG incompleteness. In this paper, we proposed a novel graph-based soft prompting framework that shifts the reasoning paradigm from node-level path traversal to subgraph-level reasoning. Specifically, we employ a Graph Neural Network (GNN) to encode extracted structural subgraphs into soft prompts, enabling LLM to reason over richer structural context and identify relevant entities beyond immediate graph neighbors, thereby reducing sensitivity to missing edges. Furthermore, we introduce a two-stage paradigm that reduces computational cost while preserving good performance: a lightweight LLM first leverages the soft prompts to identify question-relevant entities and relations, followed by a more powerful LLM for evidence-aware answer generation. Experiments on four multi-hop KBQA benchmarks show that our approach achieves state-of-the-art performance on three of them, demonstrating its effectiveness. Code is available at the repository: https://github.com/Wangshuaiia/GraSP.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
