A multi-agent LLM architecture with four artifact-driven roles produces ontologies from insurance contracts that have significantly better structural quality and modestly better queryability than a single-agent baseline, with gains driven by front-loaded planning.
Title resolution pending
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
The paper releases a benchmark of ten life-insurance contracts, a domain ontology, and 58 evidence-linked scenarios that shows ontology-driven knowledge graph queries produce more consistent and diagnosable gap/overlap results than text-only LLM inference.
citing papers explorer
-
Towards Automated Ontology Generation from Unstructured Text: A Multi-Agent LLM Approach
A multi-agent LLM architecture with four artifact-driven roles produces ontologies from insurance contracts that have significantly better structural quality and modestly better queryability than a single-agent baseline, with gains driven by front-loaded planning.
-
A Benchmark for Gap and Overlap Analysis as a Test of KG Task Readiness
The paper releases a benchmark of ten life-insurance contracts, a domain ontology, and 58 evidence-linked scenarios that shows ontology-driven knowledge graph queries produce more consistent and diagnosable gap/overlap results than text-only LLM inference.