Ontology-Guided, Hybrid Prompt Learning for Generalization in Knowledge Graph Question Answering
This addresses the transferability issue in KGQA for researchers and practitioners, enabling resource-efficient application to new knowledge graphs, though it is incremental as it builds on existing LLM and prompt learning techniques.
The paper tackles the problem of Knowledge Graph Question Answering (KGQA) systems being unable to generalize to unseen knowledge graphs without extensive retraining, by introducing OntoSCPrompt, a two-stage LLM-based approach that separates semantic parsing from KG-dependent interactions and uses ontology-guided hybrid prompt learning. It achieves performance comparable to state-of-the-art methods on datasets like CWQ, WebQSP, and LC-QuAD 1.0 without retraining, and generalizes well to unseen domain-specific KGs such as DBLP-QuAD and CoyPu.
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}