Guiding the Growth: Difficulty-Controllable Question Generation through Step-by-Step Rewriting

TL;DR

This paper introduces a new method for generating questions with controllable difficulty levels by progressively rewriting questions guided by reasoning chains, enhancing interpretability and control over question complexity.

Contribution

It redefines question difficulty based on inference steps and proposes a step-by-step rewriting framework guided by reasoning chains for better difficulty control.

Findings

Effective control over question difficulty demonstrated

Framework outperforms baselines in generating appropriately challenging questions

Automatically constructed dataset supports research and evaluation

Abstract

This paper explores the task of Difficulty-Controllable Question Generation (DCQG), which aims at generating questions with required difficulty levels. Previous research on this task mainly defines the difficulty of a question as whether it can be correctly answered by a Question Answering (QA) system, lacking interpretability and controllability. In our work, we redefine question difficulty as the number of inference steps required to answer it and argue that Question Generation (QG) systems should have stronger control over the logic of generated questions. To this end, we propose a novel framework that progressively increases question difficulty through step-by-step rewriting under the guidance of an extracted reasoning chain. A dataset is automatically constructed to facilitate the research, on which extensive experiments are conducted to test the performance of our method.