Skip to content

From Fluent Text to Ontology-Compatible Definitions: A Quality-Control Agentic Workflow

Nov 2026 · 0 citations · 34 references
Computer Science

TL;DR

Two structured-knowledge incompatibility metrics are proposed, Entity Error Rate (EER) and Logical Inconsistency Rate (LIR), to quantify entity grounding and logical consistency for LLM-generated ontology definitions and an agentic quality-control workflow is developed that effectively decreases EER while maintaining strong conventional text-generation performance.

Abstract

Biomedical ontologies are structured knowledge systems that must evolve continuously to represent newly emerging knowledge, but their manual maintenance remains time-consuming and laborintensive. Textual definitions are especially costly because they must be readable to humans and compatible with controlled entities, relations, and logical constraints. Large language models (LLMs) offer a promising way to assist ontology engineering tasks, including definition generation. However, textual plausibility does not guarantee knowledge-system compatibility. A generated definition may be fluent and close to a reference definition, yet still fail to ground its implied entities or violate ontology-level constraints. Directly inserting such definitions into ontology libraries may therefore introduce entity-level hallucinations and logical inconsistencies. To address this problem, we propose two structured-knowledge incompatibility metrics, Entity Error Rate (EER) and Logical Inconsistency Rate (LIR), to quantify entity grounding and logical consistency for LLM-generated ontology definitions. We further develop an agentic quality-control (QC) workflow that treats definition generation as an iterative process rather than a direct decoding step: it generates definitions, extracts axioms, checks entity existence and logical consistency, and uses the resulting diagnostics to drive repair loops. Comprehensive experiments on Disease Ontology, Uberon Ontology, and Uberon-ConstraintStress demonstrate that EER and LIR complement conventional reference-based metrics by evaluating whether generated content can be grounded and checked inside the target ontology. The workflow effectively decreases EER while maintaining strong conventional text-generation performance. LIR further exposes sparse ontology-level logical failures that are invisible to text similarity metrics, although their repair remains limited.

View source

Similar papers

Review

OWL-SDA: A Multi-Agent System for Generating Synthetic Data to Support Ontology Evaluation

OWL-SDA, an open-source toolkit that uses worker, supervisor and reviewer AI agents to generate synthetic RDF data from ontology context and SHACL constraints, shows that richer ontology constraints lead to faster convergence and more informative examples, while sparse ontologies require more supervision and still yiel...

Maxim Van de Wynckel, Emmelien De Roock · 0 citations

UniDataAgent: An Ontology-Grounded Agent for Enterprise Question-to-Report Automation

ChinaUnicom DataAgent (UniDataAgent) is presented, an ontology grounded system for reusable question-to-report analysis that separates semantic acquisition from online execution and has the potential to be replicated in other enterprises.

Yu-Tai Duan, Ya-Hui Zhao, Zhang-Ti Li et al. · 0 citations

Related blog posts

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.