A Novel Approach to Scalable and Automatic Topic-Controlled Question Generation in Education

2025-01-09

AI Summary

Existing automated question generation (AQG) methods for educational applications suffer from insufficient topic controllability and low precision in aligning generated questions with curricular knowledge points. Method: This paper proposes T-CQG, a topic-controllable question generation framework. It introduces a fine-grained educational topic alignment mechanism and a novel topic-relevance evaluation metric. Built upon T5-small, T-CQG integrates education-specific data construction, optimized pretraining strategies, model quantization, and context-aware data augmentation. Contribution/Results: T-CQG achieves the first instance of semantically precise alignment between curriculum knowledge points and generated questions. It simultaneously ensures lightweight deployment (small parameter count, efficient inference) and high pedagogical fidelity. Offline automatic evaluations and human assessments demonstrate significant improvements in question-topic relevance and instructional appropriateness. The framework enables cost-effective, large-scale deployment in personalized tutoring systems.

Technology Category

• Natural Language Processing: Question Answering
• Machine Learning: Calibration & Uncertainty Quantification
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies

Abstract

The development of Automatic Question Generation (QG) models has the potential to significantly improve educational practices by reducing the teacher workload associated with creating educational content. This paper introduces a novel approach to educational question generation that controls the topical focus of questions. The proposed Topic-Controlled Question Generation (T-CQG) method enhances the relevance and effectiveness of the generated content for educational purposes. Our approach uses fine-tuning on a pre-trained T5-small model, employing specially created datasets tailored to educational needs. The research further explores the impacts of pre-training strategies, quantisation, and data augmentation on the model's performance. We specifically address the challenge of generating semantically aligned questions with paragraph-level contexts, thereby improving the topic specificity of the generated questions. In addition, we introduce and explore novel evaluation methods to assess the topical relatedness of the generated questions. Our results, validated through rigorous offline and human-backed evaluations, demonstrate that the proposed models effectively generate high-quality, topic-focused questions. These models have the potential to reduce teacher workload and support personalised tutoring systems by serving as bespoke question generators. With its relatively small number of parameters, the proposals not only advance the capabilities of question generation models for handling specific educational topics but also offer a scalable solution that reduces infrastructure costs. This scalability makes them feasible for widespread use in education without reliance on proprietary large language models like ChatGPT.

Problem

• Automatic Question Generation
• Theme Control
• Personalized Education

Innovation

• T-CQG
• Topic-Related Question Generation
• Personalized Education