Guiding the Growth: Difficulty-Controllable Question Generation through Step-by-Step Rewriting
This work addresses the need for more interpretable and controllable question generation systems, particularly for educational or QA applications, though it is incremental in redefining difficulty and applying a novel method.
The paper tackles the problem of generating questions with specific difficulty levels by redefining difficulty as the number of inference steps needed to answer, and proposes a framework that uses step-by-step rewriting guided by reasoning chains to achieve this, resulting in improved performance on a new dataset.
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.