From Fluent Text to Ontology-Compatible Definitions: A Quality-Control Agentic Workflow
The paper addresses the gap between fluent LLM-generated biomedical ontology definitions and definitions that are compatible with ontology entities and logical constraints. It introduces Entity Error Rate and Logical Inconsistency Rate to measure entity grounding and logical consistency, complementing reference-based text metrics. An agentic quality-control workflow iteratively generates definitions, extracts axioms, checks entity existence and logical consistency, and uses diagnostics for repair. Experiments on Disease Ontology, Uberon, and Uberon-ConstraintStress show reduced Entity Error Rate while conventional text-generation performance remains strong; Logical Inconsistency Rate reveals failures that similarity metrics miss, though repair remains limited.
It offers a concrete evaluation and workflow approach for reducing hallucination and logical inconsistency when LLMs are used in ontology engineering.
Comments & Questions (0)
No comments yet
Be the first to comment!