A Retrieval-augmented Generation Framework for Policy-grounded Course Advising in Higher Education
Oladipo Sunday *
Department of Computer Science, School of Computing, Babcock University, Ilishan-Remo, Ogun State, Nigeria.
Kuyoro Shade
Department of Computer Science, School of Computing, Babcock University, Ilishan-Remo, Ogun State, Nigeria.
Akinwunmi Damilare
Department of Computer Science, School of Computing, Babcock University, Ilishan-Remo, Ogun State, Nigeria.
Abel Samuel
Department of Computer Science, School of Computing, Babcock University, Ilishan-Remo, Ogun State, Nigeria.
Ifeanyichukwu Princewill
Department of Computer Science, School of Computing, Babcock University, Ilishan-Remo, Ogun State, Nigeria.
Adenuga Ayomide Daniel
Department of Computer Science, School of Computing, Babcock University, Ilishan-Remo, Ogun State, Nigeria.
Ifeanyi Emeka Mathew
Department of Computer Science, School of Computing, Babcock University, Ilishan-Remo, Ogun State, Nigeria.
Udosen Alfred
Department of Computer Science, School of Computing, Babcock University, Ilishan-Remo, Ogun State, Nigeria.
*Author to whom correspondence should be addressed.
Abstract
Course advising in higher education requires students and advisers to integrate information from course catalogues, programme requirements, departmental handbooks, prerequisite rules, and institutional regulations. This study presents a Retrieval-Augmented Generation (RAG) framework for policy-grounded undergraduate course advising at Babcock University, Nigeria. The prototype combines a structured academic database, an indexed institutional knowledge base, a large language model, and a separate validation layer for prerequisite and credit-load constraints. The implementation includes student-profile management, natural-language querying, knowledge-base administration, authentication, and chat-log review. Evaluation used 18 institutional source documents segmented into 246 indexed chunks, 30 simulated student profiles, 60 advisory queries, and benchmark judgements from three academic advisers. The qualitative beta evaluation examined policy retrieval, policy grounding, prerequisite and credit-limit validation, response clarity, ambiguity handling, advising usefulness, and observed failure conditions. The findings provide formative evidence that the framework can retrieve relevant institutional information, incorporate evidence into advisory responses, and apply deterministic checks to explicit academic rules. However, context fragmentation and ambiguity in source documents remained important limitations, and the evaluation did not provide statistical performance estimates. The framework is therefore positioned as a decision-support tool that retains human oversight for ambiguous or high-stakes advising cases and requires larger controlled evaluation before measurable advising performance can be established.
Keywords: Academic advising, higher education, Retrieval-Augmented Generation, large language models, policy grounding, information retrieval, course advising, decision support, academic policy, human oversight