Ontology-Guided, Hybrid Prompt Learning for Generalization in Knowledge Graph Question Answering
Research output: Contributions to collected editions/works › Article in conference proceedings › Research › peer-review
Standard
Proceedings - 2025 19th International Conference on Semantic Computing, ICSC 2025. Institute of Electrical and Electronics Engineers Inc., 2025. p. 28-35 (Proceedings - IEEE International Conference on Semantic Computing, ICSC).
Research output: Contributions to collected editions/works › Article in conference proceedings › Research › peer-review
Harvard
APA
Vancouver
Bibtex
}
RIS
TY - CHAP
T1 - Ontology-Guided, Hybrid Prompt Learning for Generalization in Knowledge Graph Question Answering
AU - Jiang, Longquan
AU - Huang, Junbo
AU - Moller, Cedric
AU - Usbeck, Ricardo
N1 - Conference code: 19
PY - 2025
Y1 - 2025
N2 - 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 11Code: https://github.com/LongquanJiang/OntoSCPrompt.
AB - 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 11Code: https://github.com/LongquanJiang/OntoSCPrompt.
KW - Generalization
KW - KGQA
KW - LLM
KW - QA
KW - Informatics
UR - http://www.scopus.com/inward/record.url?scp=105009456479&partnerID=8YFLogxK
U2 - 10.48550/arXiv.2502.03992
DO - 10.48550/arXiv.2502.03992
M3 - Article in conference proceedings
SN - 979-8-3315-2427-2
T3 - Proceedings - IEEE International Conference on Semantic Computing, ICSC
SP - 28
EP - 35
BT - Proceedings - 2025 19th International Conference on Semantic Computing, ICSC 2025
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 19th International Conference on Semantic Computing - ICSC 2025
Y2 - 3 February 2025 through 5 February 2025
ER -