analiza aiqbench
SchemaForge introduces a schema-grounded agentic framework that significantly improves text-to-SPARQL accuracy by dynamically aligning heterogeneous knowledge graph schemas before query execution. By leveraging question-conditioned schema-slice alignment and counterfactual validation, the system achieves an average 11.5 percentage point gain in execution accuracy across major benchmarks like LC-QuAD 2.0 and Spider4SPARQL. This approach addresses a critical gap in practical KGQA where standard evaluations fail to account for partial alignments and incomplete metadata in real-world graph collections.
From Graph Retrieval to Schema Realization: Counterfactual Validation for Text-to-SPARQL over Heterogeneous Knowledge Graphs
arXiv:2508.01815v3 Announce Type: replace Abstract: 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 more than SPARQL syntax: the system must identify a graph schema that can support the predicates, entity types, joins, filters, and constraints required by the question. We present SchemaForge, a schema-grounded agentic framework for text-to-SPARQL over heterogeneous KG collections. Its central mechanism is question-conditioned schema-slice alignment: weak graph evidence first identifies plausible graphs, while stronger schema evidence determines whether a local schema slice can realize the intended query. The selected schema slice then constrains query generation and verification before execution. When only one graph is available, the same formulation reduces to standard single-KG text-to-SPARQL with schema grounding. We evaluate SchemaForge on LC-QuAD 2.0, QALD-9 Plus, QALD-10, and Spider4SPARQL. Across the four public benchmarks, SchemaForge improves execution accuracy over the strongest matched agent baseline by 11.50 percentage points on average. On Spider4SPARQL, SchemaForge improves execution accuracy from 54.86% to 64.18% and achieves 73.0% Top-1 and 97.0% Top-3 graph allocation accuracy. These results show that moving from weak graph evidence to schema-specific query commitments, together with counterfactual answer-set checks, improves executable query generation over heterogeneous knowledge graphs.
Abstract: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 more than SPARQL syntax: the system must identify a graph schema that can support the predicates, entity types, joins, filters, and constraints required by the question. We present SchemaForge, a schema-grounded agentic framework for text-to-SPARQL over heterogeneous KG collections. Its central mechanism is question-conditioned schema-slice alignment: weak graph evidence first identifies plausible graphs, while stronger schema evidence determines whether a local schema slice can realize the intended query. The selected schema slice then constrains query generation and verification before execution. When only one graph is available, the same formulation reduces to standard single-KG text-to-SPARQL with schema grounding. We evaluate SchemaForge on LC-QuAD 2.0, QALD-9 Plus, QALD-10, and Spider4SPARQL. Across the four public benchmarks, SchemaForge improves execution accuracy over the strongest matched agent baseline by 11.50 percentage points on average. On Spider4SPARQL, SchemaForge improves execution accuracy from 54.86% to 64.18% and achieves 73.0% Top-1 and 97.0% Top-3 graph allocation accuracy. These results show that moving from weak graph evidence to schema-specific query commitments, together with counterfactual answer-set checks, improves executable query generation over heterogeneous knowledge graphs.
Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
arXiv:2508.01815 [cs.CL]
(or arXiv:2508.01815v3 [cs.CL] for this version)
Text integral sub licența deschisă a publicației · 238 cuvinte
Subiecte conexe
The AI application your team can actually stand behind
Neo4j · 21 sept. 2026
How Reactiv automates mobile commerce 80% faster with Amazon Bedrock AgentCore
AWS · 22 sept. 2026
Decision-Aware Memory Cards: Counterfactual-Inspired Context Selection and Compression for Tool-Using LLM Agents
arXiv · 9 iun. 2026
Clustering billions of products for agentic commerce with Catalog API
Shopify Engineering Blog · 17 iun. 2026