Retrieval-Augmented Question Answering for Academic Regulations

Helping Students Navigate University Policies

Abstract

University regulations are spread across many documents, and students frequently ask staff questions that the documents already answer. This study builds a retrieval-augmented question answering assistant that retrieves relevant passages from 64 regulation documents and generates answers that cite their sources. On 250 real student questions, answers were judged correct and complete in 82% of cases, compared with 61% for the same language model without retrieval. Citing the source passage allowed staff to verify answers quickly, and the assistant declined to answer when no relevant passage was found. Most errors came from outdated documents that had not yet been removed from the collection. The findings highlight that document governance matters as much as model choice for reliable regulation assistants.