Retrieval-Augmented Question Answering for Academic Regulations

Helping Students Navigate University Policies

Putri Anggraini, Bayu Firmansyah

Jurnal Teknologi dan Inovasi, Vol. 1 No. 2 (2026), pp. 93-100

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 Most errors came from outdated documents that had not yet been removed from the collection.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.

Keywords: retrieval-augmented generation; question answering; large language models; academic regulations; chatbot

1. Introduction

This section introduces the problem of natural language processing addressed in this study, reviews the main approaches reported in prior work, and states the research objectives.

2. Methods

We describe the data, the proposed approach, the baselines, and the evaluation protocol used to assess the results summarised in the abstract.

3. Results and Discussion

The results are presented and compared with the baselines. Limitations and practical implications for deployment are discussed.

4. Conclusion

The study shows that the proposed approach is effective for the stated objectives and outlines directions for future work.

References

  1. Lewis, P., Perez, E., Piktus, A., Petroni, F., Karpukhin, V., Goyal, N., Küttler, H., Lewis, M., Yih, W., Rocktäschel, T., Riedel, S., & Kiela, D. (2020). Retrieval-augmented generation for knowledge-intensive NLP tasks. Advances in Neural Information Processing Systems, 33, 9459–9474.
  2. Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, Ł., & Polosukhin, I. (2017). Attention is all you need. Advances in Neural Information Processing Systems, 30.
  3. Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019). BERT: Pre-training of deep bidirectional transformers for language understanding. Proceedings of NAACL-HLT 2019, 4171–4186.
  4. Reimers, N., & Gurevych, I. (2019). Sentence-BERT: Sentence embeddings using Siamese BERT-networks. Proceedings of EMNLP-IJCNLP 2019, 3982–3992.