Neurosymbolic research often assumes an existing symbolic specification, leaving the acquisition and formalization of requirements and constraints largely ignored. We introduce an architecture that uses an OWL configuration ontology to mediate between neural constraint sources and downstream consumers.
In this framework, LLM assistants elicit soft stakeholder preferences while hardware specifications define hard physical and engineering limits. The ontology unifies these heterogeneous inputs into description‑logic entities, employs DL reasoning to detect unsatisfiability, and produces symbolic explanations that enable LLMs to interactively renegotiate terms with users.
Any remaining conflicts are resolved downstream via a priority‑based relaxation mechanism. We demonstrate the approach on a microgrid use case from the FLEXI project and argue for its generalizability to multi‑stakeholder domains where constraint acquisition is distributed across human and automated sources of unequal authority.
Review