AI RESEARCH
From Graph Retrieval to Schema Realization: Counterfactual Validation for Text-to-SPARQL over Heterogeneous Knowledge Graphs
arXiv CS.AI
•
ArXi:2508.01815v2 Announce Type: replace-cross Text-to-SPARQL maps natural-language questions to executable SPARQL queries over RDF knowledge graphs. While standard evaluations often fix the target graph in advance, practical knowledge graph question answering (KGQA) may involve heterogeneous graph collections with different schemas, partial alignments, and incomplete metadata. In this setting, query generation depends on than SPARQL syntax: the system must identify a graph schema that can the predicates, entity types, joins, filters, and constraints required by the question.