Information-Needs-Guided Virtual Knowledge Graph Enrichment via Large Language Models

Ren, Lin; Xiao, Guohui; Qi, Guilin; Du, Wenjie; Geng, Yishuai; Xue, Haohan; Yue, Zhiyan; Li, Mingxuan; Di Panfilo, Marco; Lanti, Davide; Hamaz, Kamal; Ding, Linfang

doi:10.24963/ijcai.2026/448

Information-Needs-Guided Virtual Knowledge Graph Enrichment via Large Language Models

Lin Ren, Guohui Xiao, Guilin Qi, Wenjie Du, Yishuai Geng, Haohan Xue, Zhiyan Yue, Mingxuan Li, Marco Di Panfilo, Davide Lanti, Kamal Hamaz, Linfang Ding

Download BibTeX Cite

Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence. Main Track. Pages 4026-4034.

https://doi.org/10.24963/ijcai.2026/448

Keywords

Knowledge Representation and Reasoning: Description logics and ontologies
Knowledge Representation and Reasoning: Semantic Web

Abstract

Virtual Knowledge Graphs (VKGs) provide an effective solution for data integration by mapping heterogeneous data sources to a unified ontology.

However, existing VKG construction frameworks primarily focus on one-shot construction, which often results in partial data coverage and support for only initial information needs.

After the VKG has been deployed, new information needs will inevitably arise over time.

Therefore, enriching VKGs to support evolving information needs remains an expert-intensive iterative task.

In this work, we formulate the task of Information-Needs-Guided VKG Enrichment (IN-VKGE), and propose an iterative framework that leverages large language models to assess whether information needs can be supported using SPARQL execution feedback and generate ontology and mapping enrichment proposals.

Experiments on two real-world VKGs show that our approach outperforms existing paradigms, and produces enrichment proposals that receive high expert ratings for effectively resolving the identified information needs.

Lin Ren, Guohui Xiao, Guilin Qi, Wenjie Du, Yishuai Geng, Haohan Xue, Zhiyan Yue, Mingxuan Li, Marco Di Panfilo, Davide Lanti, Kamal Hamaz, and Linfang Ding. 2026. Information-Needs-Guided Virtual Knowledge Graph Enrichment via Large Language Models. In Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-26. IJCAI, 4026–4034. https://doi.org/10.24963/ijcai.2026/448

@inproceedings{ijcai2026p448,
  title     = {Information-Needs-Guided Virtual Knowledge Graph Enrichment via Large Language Models},
  author    = {Ren, Lin and Xiao, Guohui and Qi, Guilin and Du, Wenjie and Geng, Yishuai and Xue, Haohan and Yue, Zhiyan and Li, Mingxuan and Di Panfilo, Marco and Lanti, Davide and Hamaz, Kamal and Ding, Linfang},
  booktitle = {Proceedings of the Thirty-Fifth International Joint Conference on
               Artificial Intelligence, {IJCAI-26}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {Diego Calvanese},
  pages     = {4026--4034},
  year      = {2026},
  month     = {8},
  note      = {Main Track},
  doi       = {10.24963/ijcai.2026/448},
  url       = {https://doi.org/10.24963/ijcai.2026/448},
}

TY  - CPAPER
TI  - Information-Needs-Guided Virtual Knowledge Graph Enrichment via Large Language Models
AU  - Ren, Lin
AU  - Xiao, Guohui
AU  - Qi, Guilin
AU  - Du, Wenjie
AU  - Geng, Yishuai
AU  - Xue, Haohan
AU  - Yue, Zhiyan
AU  - Li, Mingxuan
AU  - Di Panfilo, Marco
AU  - Lanti, Davide
AU  - Hamaz, Kamal
AU  - Ding, Linfang
T2  - Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-26
PB  - International Joint Conferences on Artificial Intelligence Organization
PY  - 2026
SP  - 4026
EP  - 4034
DO  - 10.24963/ijcai.2026/448
UR  - https://doi.org/10.24963/ijcai.2026/448
ER  -