Automatic Question & Answer Generation Using Generative Large Language Model (LLM)

TL;DR

This paper presents an automated question and answer generation system using a fine-tuned large language model, aimed at simplifying educational assessments and reducing manual effort for educators.

Contribution

It introduces a novel approach to fine-tune a generative LLM with the RACE dataset and prompt engineering for customizable question styles in educational assessments.

Findings

Effective question and answer generation demonstrated

Customization of question styles achieved via prompt engineering

Potential to streamline educational evaluation processes

Abstract

In the realm of education, student evaluation holds equal significance to imparting knowledge. To be evaluated, students usually need to go through text-based academic assessment methods. Instructors need to make a diverse set of questions that need to be fair for all students to prove their adequacy over a particular topic. This can prove to be quite challenging as they may need to manually go through several different lecture materials. Our objective is to make this whole process much easier by implementing Automatic Question Answer Generation(AQAG), using a fine-tuned generative LLM. For tailoring the instructor's preferred question style (MCQ, conceptual, or factual questions), Prompt Engineering (PE) is being utilized. In this research, we propose to leverage unsupervised learning methods in NLP, primarily focusing on the English language. This approach empowers the base Meta-Llama 2-7B model to integrate the RACE dataset as training data for the fine-tuning process. Creating a customized model that will offer efficient solutions for educators, instructors, and individuals engaged in text-based evaluations. A reliable and efficient tool for generating questions and answers can free up valuable time and resources, thus streamlining their evaluation processes.