EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A DISTILBERT-Driven Course-Aware Retrieval-Augmented Framework for Educational Question Answering

Raavi Srikanth, Pottasiri Chandra Mohanarai

Adolescência e Saúde · 04.10.2026 · 2847-2862

DOI: 10.67440/ahj.vi.2863 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Adolescência e Saúde, online erschienen am 04.10.2026. Verfasst von Raavi Srikanth und 1 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

With the advent of artificial intelligence and natural language processing, new possibilities arose to build intelligent educational question-answering systems to provide relevant academic information to learners through natural language interaction. However, traditional approaches to question-answering could be ineffective in identifying what information a learner is interested in and therefore finding the relevant knowledge chunks in the course. In order to overcome the above issue, this paper introduces a Course-Aware Retrieval-Augmented Generation Framework Employing DistilBERT-based Intent Classification for Intelligent Questions Answering in Education. The proposed framework consists of two modules: a light-weight transformer-based intent classification module and a retrieval module based on course-awareness. This provides a structured mapping between the learner's question, question information category, and course information. It employs the Educational Questions & Answers dataset (12,571 question-answer pairs) that has been cleaned to get 11,702 valid records. The questions were broken down into five educational intents: level, price, generic, free/paid, enrollment, subject, and beginner suitability, excluding the generic category, training the classifiers. The 18,720 labeled data samples in the stratified dataset were split into both a training and validation subset and DistilBERT was fine tuned for intent classification. The obtained accuracy, precision, recall, F1-score at the selected first training epoch show that the classification of the defined educational intent categories has been accomplished in a very effective way with precision of 99.9466%, recall of 99.9563% and F1 score of 99.9541%. Based on the findings, we conclude that DistilBERT is a suitable layer for understanding the intention for educational retrieval-augmented question answering. However, this classification performance cannot be understood as end-to-end RAG answer accuracy as this is only based on intent-classification performance. The areas of future development will involve human annotated intent datasets, expanded educational domains, multilingual and code-mixed queries, improvements to hybrid retrieval, reranking, and complete end-to-end assessment of retrieval relevance, answer faithfulness, and answer quality.

Zitieren

APA

Srikanth, R., & Mohanarai, P. C. (2026). A DISTILBERT-Driven Course-Aware Retrieval-Augmented Framework for Educational Question Answering. Adolescência e Saúde, 2847-2862. https://doi.org/10.67440/ahj.vi.2863

Vancouver

Srikanth R, Mohanarai PC. A DISTILBERT-Driven Course-Aware Retrieval-Augmented Framework for Educational Question Answering. Adolescência e Saúde. 2026:2847-2862. doi:10.67440/ahj.vi.2863

BibTeX
@article{Srikanth2026,
  author = {Srikanth, Raavi and Mohanarai, Pottasiri Chandra},
  title = {A DISTILBERT-Driven Course-Aware Retrieval-Augmented Framework for Educational Question Answering},
  journal = {Adolescência e Saúde},
  year = {2026},
  pages = {2847--2862},
  doi = {10.67440/ahj.vi.2863}
}
Kostenlos starten →