Topology-Aware Reasoning over Incomplete Knowledge Graph with Graph-Based Soft Prompting

TL;DR

This paper introduces a graph-based soft prompting method using GNNs to improve reasoning over incomplete knowledge graphs in KBQA, reducing reliance on explicit edge traversal.

Contribution

It proposes a novel subgraph-level reasoning framework with a two-stage paradigm, enhancing robustness to KG incompleteness and achieving state-of-the-art results.

Findings

Achieved state-of-the-art performance on three KBQA benchmarks.

Reduced sensitivity to missing edges in knowledge graphs.

Introduced a two-stage reasoning paradigm with cost-effective computation.

Abstract

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.