SALT-KG: A Benchmark for Semantics-Aware Learning on Enterprise Tables

TL;DR

SALT-KG introduces a benchmark for evaluating models that reason over enterprise tables with integrated structured business knowledge, emphasizing semantics-aware learning for improved understanding of relational and contextual data.

Contribution

It extends the SALT benchmark by linking relational data with a structured knowledge graph, enabling evaluation of semantics-aware reasoning in enterprise table prediction.

Findings

Metadata features offer modest prediction improvements.

Models struggle to leverage semantics in relational context.

SALT-KG provides a foundation for semantically grounded tabular models.

Abstract

Building upon the SALT benchmark for relational prediction (Klein et al., 2024), we introduce SALT-KG, a benchmark for semantics-aware learning on enterprise tables. SALT-KG extends SALT by linking its multi-table transactional data with a structured Operational Business Knowledge represented in a Metadata Knowledge Graph (OBKG) that captures field-level descriptions, relational dependencies, and business object types. This extension enables evaluation of models that jointly reason over tabular evidence and contextual semantics, an increasingly critical capability for foundation models on structured data. Empirical analysis reveals that while metadata-derived features yield modest improvements in classical prediction metrics, these metadata features consistently highlight gaps in the ability of models to leverage semantics in relational context. By reframing tabular prediction as semantics-conditioned reasoning, SALT-KG establishes a benchmark to advance tabular foundation models grounded in declarative knowledge, providing the first empirical step toward semantically linked tables in structured data at enterprise scale.