What Does an Ontology Catch? Curated, LLM-Generated and Data-Derived Ontologies as Checkers of LLM Agents over Knowledge Graphs
This work accounts for what ontology-derived checks catch and what they wrongly flag, and shows how each source trades caught errors against false alarms, how a curated schema used as published can contradict its own data, which errors structural checks miss, and whether combining sources or giving the agent the checke...
Michał Orzechowski, Rund Tawfiq, T. Kościółek
· 0 citations