QOG:Question and Options Generation based on Language Model

TL;DR

This paper introduces QOG, a question and options generation task using fine-tuned sequence-to-sequence language models, demonstrating efficiency and competitiveness with large models like Llama 3-8B.

Contribution

It develops and evaluates three fine-tuned sequence-to-sequence models for QOG, showing their effectiveness and efficiency over existing methods.

Findings

End-to-end QOG model is computationally efficient.

Models outperform other methods in stability and performance.

QOG models are competitive with Llama 3-8B.

Abstract

Question-Options Generation (QOG) is a task that involves generating a set of question-options pairs given context. This task has various applications, including fine-tuning large models, information retrieval, and automated multiple-choice question generation for education. In this paper, we develop QOG models using three different methods based on fine-tuning sequence-to-sequence language models (LMs). Experiments demonstrate that the end-to-end QOG model is computationally efficient and stable during both training and inference, outperforming other methods. Furthermore, our analysis indicates that our QOG models are competitive on the QOG task compared to the large language model Llama 3-8B.