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

TL;DR

OntoSCPrompt introduces an ontology-guided, hybrid prompt learning approach for KGQA that generalizes across different knowledge graphs without retraining, leveraging a two-stage semantic parsing and KG-specific query filling process.

Contribution

The paper proposes a novel LLM-based KGQA method with a two-stage architecture and ontology-guided hybrid prompts, enabling effective generalization to unseen KGs without retraining.

Findings

Achieves state-of-the-art performance on multiple KGQA datasets.

Effectively generalizes to unseen domain-specific knowledge graphs.

Operates resource-efficiently without retraining.

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}