Search papers, labs, and topics across Lattice.
This paper introduces SAGA, a training-free framework that enhances agentic text-to-SPARQL generation by implementing schema-aware grounding to improve knowledge base question answering. By maintaining a bidirectional type state and filtering incompatible property candidates, SAGA effectively reduces the search space and minimizes the occurrence of semantically invalid triple patterns. The results demonstrate that SAGA outperforms existing methods across nine benchmark settings, achieving the highest F1 scores and exact-match accuracy while significantly decreasing empty-result queries.
SAGA reduces the incidence of empty-result queries by systematically grounding SPARQL generation in schema constraints, outperforming existing methods in accuracy across multiple benchmarks.
Complex knowledge base question answering (KBQA) is commonly approached through either information retrieval over a question-specific subgraph or semantic parsing into an executable logical form. We study the latter paradigm. Recent large language model agents make semantic parsing interactive: they alternate between reasoning, querying the knowledge base, and extending a partial SPARQL query. This interleaving reduces reliance on one-shot generation, but makes the quality of \emph{KB grounding} depend on what the interaction tools expose. Existing agents retrieve or prune candidate properties mainly through lexical relevance and instance-level observations, without systematically conditioning on entity types, property domains and ranges, or the expected answer type. We call this failure mode \emph{type-blind grounding}. It enlarges the grounding search space and often produces plausible-looking but semantically incompatible triple patterns that execute to empty results. We propose SAGA (\underline{S}chema-\underline{A}ware \underline{G}rounding for \underline{A}gentic Text-to-SPARQL Generation), a training-free framework that turns property exploration into a schema-constrained grounding operation. SAGA maintains a persistent bidirectional type state, filters known-incompatible property candidates at construction time, presents the remaining graph patterns in a compact schema-annotated format, and handles missing schema information permissively through empirical and trace-local evidence. Across nine benchmark settings over Wikidata and Freebase, SAGA achieves the highest F1 on all nine settings and the highest exact-match accuracy on eight, while reducing empty-result queries across all reported Wikidata settings.
