What Does an Ontology Catch? Curated, LLM-Generated and Data-Derived Ontologies as Checkers of LLM Agents over Knowledge Graphs

The paper investigates how different types of ontologies—curated, LLM-generated, and data-derived—serve as checkers for large language model agents answering questions over knowledge graphs. By evaluating these ontologies as prompt context, as checkers, or both, across both open-weight and proprietary agents on public and a large private graph, the study quantifies the trade-offs between errors caught and false alarms. It finds that curated ontologies can flag more correct answers than other sources but are only marginally more precise than random, and that combining sources or providing specific feedback offers limited benefits.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

• llms
• agents