Ontology-Guided, Hybrid Prompt Learning for Generalization in Knowledge Graph Question Answering

2025-02-06

AI Summary

Existing knowledge graph question answering (KGQA) systems heavily rely on specific knowledge graphs (e.g., Wikidata, DBpedia) and struggle with zero-shot transfer to unseen graphs (e.g., DBLP-QuAD, CoyPu), primarily due to cross-graph schema and structural heterogeneity. Method: We propose OntoSCPrompt, a two-stage large language model (LLM) framework: (1) ontology-guided generation of SPARQL structural templates, and (2) injection of graph-specific information. It introduces the first ontology-driven hybrid prompting mechanism, decoupling semantic parsing from graph interaction, and integrates task-customized constrained decoding with syntactic validation to ensure query executability. Contribution/Results: OntoSCPrompt achieves state-of-the-art performance on CWQ, WebQSP, and LC-QuAD 1.0 without retraining. It significantly enhances cross-graph generalization while substantially reducing computational and annotation overhead.

Technology Category

• Knowledge Representation and Reasoning: Ontologies
• Data Mining & Knowledge Management: Linked Open Data, Knowledge Graphs & KB Completion
• Natural Language Processing: Question Answering

Application Category

• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Most existing Knowledge Graph Question Answering (KGQA) approaches are designed for a specific KG, such as Wikidata, DBpedia or Freebase. Due to the heterogeneity of the underlying graph schema, topology and assertions, most KGQA systems cannot be transferred to unseen Knowledge Graphs (KGs) without resource-intensive training data. We present OntoSCPrompt, a novel Large Language Model (LLM)-based KGQA approach with a two-stage architecture that separates semantic parsing from KG-dependent interactions. OntoSCPrompt first generates a SPARQL query structure (including SPARQL keywords such as SELECT, ASK, WHERE and placeholders for missing tokens) and then fills them with KG-specific information. To enhance the understanding of the underlying KG, we present an ontology-guided, hybrid prompt learning strategy that integrates KG ontology into the learning process of hybrid prompts (e.g., discrete and continuous vectors). We also present several task-specific decoding strategies to ensure the correctness and executability of generated SPARQL queries in both stages. Experimental results demonstrate that OntoSCPrompt performs as well as SOTA approaches without retraining on a number of KGQA datasets such as CWQ, WebQSP and LC-QuAD 1.0 in a resource-efficient manner and can generalize well to unseen domain-specific KGs like DBLP-QuAD and CoyPu KG Code: href{https://github.com/LongquanJiang/OntoSCPrompt}{https://github.com/LongquanJiang/OntoSCPrompt}

Problem

• Generalizing Knowledge Graph Question Answering to unseen KGs
• Reducing resource-intensive training for KGQA systems
• Enhancing KG understanding with ontology-guided prompt learning

Innovation

• Ontology-guided hybrid prompts
• Two-stage SPARQL generation
• Task-specific decoding strategies