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

arXiv: https://arxiv.org/abs/2105.11698 · HTML: https://mlsanity.com/paper/2105.11698/

## Key facts

- Cited by 30 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 37 references that are in the map.
- First posted on arXiv 25 May 2021.

## Builds on (most cited first, 23 of 23)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [HuggingFace's Transformers: State-of-the-art Natural Language Processing](https://mlsanity.com/paper/1910.03771/) (2019)
- [CIDEr: Consensus-based Image Description Evaluation](https://mlsanity.com/paper/1411.5726/) (2014)
- [Decoupled Weight Decay Regularization](https://mlsanity.com/paper/1711.05101/) (2017)
- [The Web as a Knowledge-base for Answering Complex Questions](https://mlsanity.com/paper/1803.06643/) (2018)
- [End-to-end Neural Coreference Resolution](https://mlsanity.com/paper/1707.07045/) (2017)
- [Multi-hop Reading Comprehension through Question Decomposition and Rescoring](https://mlsanity.com/paper/1906.02916/) (2019)
- [Question Rewriting for Conversational Question Answering](https://mlsanity.com/paper/2004.14652/) (2020)
- [Neural Question Generation from Text: A Preliminary Study](https://mlsanity.com/paper/1704.01792/) (2017)
- [Text Modular Networks: Learning to Decompose Tasks in the Language of Existing Models](https://mlsanity.com/paper/2009.00751/) (2020)
- [Efficient Probabilistic Logic Reasoning with Graph Neural Networks](https://mlsanity.com/paper/2001.11850/) (2020)
- [Recent Advances in Neural Question Generation](https://mlsanity.com/paper/1905.08949/) (2019)
- [Asking Questions the Human Way: Scalable Question-Answer Generation from Text Corpus](https://mlsanity.com/paper/2002.00748/) (2020)
- [Using Local Knowledge Graph Construction to Scale Seq2Seq Models to Multi-Document Inputs](https://mlsanity.com/paper/1910.08435/) (2019)
- [Semantic Graphs for Generating Deep Questions](https://mlsanity.com/paper/2004.12704/) (2020)
- [Improving Neural Question Generation using Answer Separation](https://mlsanity.com/paper/1809.02393/) (2018)
- [Learning to Generate Questions by Learning What not to Generate](https://mlsanity.com/paper/1902.10418/) (2019)
- [Let Me Know What to Ask: Interrogative-Word-Aware Question Generation](https://mlsanity.com/paper/1910.13794/) (2019)

## Built on by (most cited first, 30 of 30)

- [Varifocal Question Generation for Fact-checking](https://mlsanity.com/paper/2210.12400/) (2022)
- [Multiple-Choice Question Generation: Towards an Automated Assessment Framework](https://mlsanity.com/paper/2209.11830/) (2022)
- [Towards Process-Oriented, Modular, and Versatile Question Generation that Meets Educational Needs](https://mlsanity.com/paper/2205.00355/) (2022)
- [FrameBERT: Conceptual Metaphor Detection with Frame Embedding Learning](https://mlsanity.com/paper/2302.04834/) (2023)
- [RQUGE: Reference-Free Metric for Evaluating Question Generation by Answering the Question](https://mlsanity.com/paper/2211.01482/) (2022)
- [QGEval: Benchmarking Multi-dimensional Evaluation for Question Generation](https://mlsanity.com/paper/2406.05707/) (2024)
- [NGEP: A Graph-based Event Planning Framework for Story Generation](https://mlsanity.com/paper/2210.10602/) (2022)
- [Metaphor Detection with Effective Context Denoising](https://mlsanity.com/paper/2302.05611/) (2023)
- [QRelScore: Better Evaluating Generated Questions with Deeper Understanding of Context-aware Relevance](https://mlsanity.com/paper/2204.13921/) (2022)
- [Writing-RL: Advancing Long-form Writing via Adaptive Curriculum Reinforcement Learning](https://mlsanity.com/paper/2506.05760/) (2025)
- [Explainable Multi-hop Question Generation: An End-to-End Approach without Intermediate Question Labeling](https://mlsanity.com/paper/2404.00571/) (2024)
- [Diversity Enhanced Narrative Question Generation for Storybooks](https://mlsanity.com/paper/2310.16446/) (2023)
- [Event Transition Planning for Open-ended Text Generation](https://mlsanity.com/paper/2204.09453/) (2022)
- [Synthetic Context Generation for Question Generation](https://mlsanity.com/paper/2406.13188/) (2024)
- [AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs](https://mlsanity.com/paper/2505.21389/) (2025)
- [KNIGHT: Knowledge Graph-Driven Multiple-Choice Question Generation with Adaptive Hardness Calibration](https://mlsanity.com/paper/2602.20135/) (2026)
- [Feeding What You Need by Understanding What You Learned](https://mlsanity.com/paper/2203.02753/) (2022)
- [Survey of Natural Language Processing for Education: Taxonomy, Systematic Review, and Future Trends](https://mlsanity.com/paper/2401.07518/) (2024)
- [Increasing the Difficulty of Automatically Generated Questions via Reinforcement Learning with Synthetic Preference](https://mlsanity.com/paper/2410.08289/) (2024)
- [ECIS-VQG: Generation of Entity-centric Information-seeking Questions from Videos](https://mlsanity.com/paper/2410.09776/) (2024)
- [HopWeaver: Cross-Document Synthesis of High-Quality and Authentic Multi-Hop Questions](https://mlsanity.com/paper/2505.15087/) (2025)
- [SkillQG: Learning to Generate Question for Reading Comprehension Assessment](https://mlsanity.com/paper/2305.04737/) (2023)
- [Advancing Question Generation with Joint Narrative and Difficulty Control](https://mlsanity.com/paper/2506.06812/) (2025)
- [Difficulty-Controllable Multiple-Choice Question Generation Using Large Language Models and Direct Preference Optimization](https://mlsanity.com/paper/2510.19265/) (2025)
- [IRB: Automated Generation of Robust Factuality Benchmarks](https://mlsanity.com/paper/2602.08070/) (2026)
- [Contrastive Learning for Inference in Dialogue](https://mlsanity.com/paper/2310.12467/) (2023)
- [From Model to Classroom: Evaluating Generated MCQs for Portuguese with Narrative and Difficulty Concerns](https://mlsanity.com/paper/2506.15598/) (2025)
- [Generating Multiple-Choice Knowledge Questions with Interpretable Difficulty Estimation using Knowledge Graphs and Large Language Models](https://mlsanity.com/paper/2604.10748/) (2026)
- [MUSE: Benchmarking Large Vision-Language Models on Multi-Modal Understanding in Situated Education](https://mlsanity.com/paper/2609.19088/) (2026)
- [ChemCLIR-Bench: Benchmarking Cross-Lingual Information Retrieval in Multilingual Chemical Patents](https://mlsanity.com/paper/2609.23231/) (2026)

## Abstract (arXiv)

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.