Empirical 2x2 factorial study on 6 statistical datasets shows format and schema constraints in LLM-based KG construction from CSV tables produce super-additive fidelity loss up to +1.180, with mismatched pairs falling below baseline, plus release of CSVFidelity-Bench.
and Baranzini, Sergio E
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.AI 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Empirical comparison on small industrial KG finds vector retrieval fails on structural queries while LLM planner with typed graph operators achieves higher F1 and generalizes to unseen queries.
citing papers explorer
-
Format-Constraint Coupling in Knowledge Graph Construction from Statistical Tables
Empirical 2x2 factorial study on 6 statistical datasets shows format and schema constraints in LLM-based KG construction from CSV tables produce super-additive fidelity loss up to +1.180, with mismatched pairs falling below baseline, plus release of CSVFidelity-Bench.
-
Beyond Vector Similarity: A Structural Analysis of Graph-Augmented Retrieval for Industrial Knowledge Graphs
Empirical comparison on small industrial KG finds vector retrieval fails on structural queries while LLM planner with typed graph operators achieves higher F1 and generalizes to unseen queries.