Automated Generation of Curriculum-Aligned Multiple-Choice Questions for Malaysian Secondary Mathematics Using Generative AI

TL;DR

This paper presents a novel RAG-based pipeline for generating curriculum-aligned multiple-choice questions in Bahasa Melayu using GPT-4o, with automated evaluation methods demonstrating improved factual accuracy and curriculum relevance.

Contribution

It introduces and compares four incremental pipelines, including RAG approaches, for generating curriculum-specific MCQs in a low-resource language, with a new evaluation framework.

Findings

RAG pipelines outperform non-grounded prompting in curriculum alignment

Automated evaluation effectively measures factual validity and curriculum relevance

Manual pipeline offers fine-grained control with comparable quality

Abstract

This paper addresses the critical need for scalable and high-quality educational assessment tools within the Malaysian education system. It highlights the potential of Generative AI (GenAI) while acknowledging the significant challenges of ensuring factual accuracy and curriculum alignment, especially for low-resource languages like Bahasa Melayu. This research introduces and compares four incremental pipelines for generating Form 1 Mathematics multiple-choice questions (MCQs) in Bahasa Melayu using OpenAI's GPT-4o. The methods range from non-grounded prompting (structured and basic) to Retrieval-Augmented Generation (RAG) approaches (one using the LangChain framework, one implemented manually). The system is grounded in official curriculum documents, including teacher-prepared notes and the yearly teaching plan (RPT). A dual-pronged automated evaluation framework is employed to assess the generated questions. Curriculum alignment is measured using Semantic Textual Similarity (STS) against the RPT, while contextual validity is verified through a novel RAG-based Question-Answering (RAG-QA) method. The results demonstrate that RAG-based pipelines significantly outperform non-grounded prompting methods, producing questions with higher curriculum alignment and factual validity. The study further analyzes the trade-offs between the ease of implementation of framework-based RAG and the fine-grained control offered by a manual pipeline. This work presents a validated methodology for generating curriculum-specific educational content in a low-resource language, introduces a symbiotic RAG-QA evaluation technique, and provides actionable insights for the development and deployment of practical EdTech solutions in Malaysia and similar regions.