Yishuai Geng

2 accepted papers

2026

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

Lin Ren, Guohui Xiao, Guilin Qi, Wenjie Du, Yishuai Geng, Haohan Xue +6

IJCAI 2026

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 in

Cited by 0 Scholar ↗

2026

NaVQA: Mitigating Silent Failures in Question Answering over Virtual Knowledge Graph

Guohui Xiao, Haohan Xue, Lin Ren, Yishuai Geng, Guilin Qi, Shenyu Zhang +4

IJCAI 2026

Virtual Knowledge Graphs (VKGs) provide unified access to legacy relational data sources through a high-level ontology modeling a domain of interest. The content of the ontology elements (classes and properties) is virtually mapped to underlying data sources through declarative mappings. The standar

Cited by 0 Scholar ↗