Bridging the Trust Gap: A Hybrid Intuitive-Rational Architecture for Certified University Assistants
TL;DR
A proof-of-concept neuro-symbolic architecture for “certified” academic advising that shows how an LLM-based university assistant can be connected to an auditable and reproducible symbolic layer, while preserving a clear separation between linguistic interaction and formal regulatory reasoning.
Abstract
Large Language Models (LLMs) have improved conversational access to university services, but their answers remain difficult to verify in regulation-sensitive domains. This paper presents a proof-of-concept neuro-symbolic architecture for “certified” academic advising. The system combines ParsyBot as a conversational interface with a Prologbased reasoning layer constructed from selected clauses of the Başkent University Undergraduate Education and Exam Regulation. In the proposed architecture, the LLM does not make normative decisions. It assists the drafting of symbolic rules, maps a small set of controlled natural-language intents into Prolog queries and verbalizes the symbolic output. The compliance decision itself is produced by the Prolog engine. We demonstrate the approach on representative clauses concerning attendance-based F2 failure, resit ineligibility, GGA-based enrollment restriction, course repetition, and a lightweight planning scenario. The results show how an LLM-based university assistant can be connected to an auditable and reproducible symbolic layer, while preserving a clear separation between linguistic interaction and formal regulatory reasoning.