Beyond Predefined Schemas: TRACE-KG for Context-Enriched Knowledge Graphs from Complex Documents

TL;DR

TRACE-KG is a multimodal framework that constructs context-enriched, traceable knowledge graphs from complex documents without relying on predefined schemas or ontologies.

Contribution

It introduces a novel method for joint construction of knowledge graphs and schemas, capturing conditional relations and organizing entities without predefined ontologies.

Findings

Produces structurally coherent, traceable knowledge graphs

Offers a practical alternative to existing ontology-driven and schema-free methods

Effectively handles dense, context-dependent information in technical documents

Abstract

Knowledge graph construction typically relies either on predefined ontologies or on schema-free extraction. Ontology-driven pipelines enforce consistent typing but require costly schema design and maintenance, whereas schema-free methods often produce fragmented graphs with weak global organization, especially in long technical documents with dense, context-dependent information. We propose TRACE-KG (Text-dRiven schemA for Context-Enriched Knowledge Graphs), a multimodal framework that jointly constructs a context-enriched knowledge graph and an induced schema without assuming a predefined ontology. TRACE-KG captures conditional relations through structured qualifiers and organizes entities and relations using a data-driven schema that serves as a reusable semantic scaffold while preserving full traceability to the source evidence. Experiments show that TRACE-KG produces structurally coherent, traceable knowledge graphs and offers a practical alternative to both ontology-driven and schema-free construction pipelines.