# Simple or Complex? Complexity-Controllable Question Generation with Soft Templates and Deep Mixture of Experts Model

arXiv: https://arxiv.org/abs/2110.06560 · HTML: https://mlsanity.com/paper/2110.06560/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Placed in MoE large language models, one of 12 directions in Mixture-of-experts.
- Builds on 22 of its 37 references that are in the map.
- First posted on arXiv 13 Oct 2021.

## Placed in

- Mixture-of-experts / [MoE large language models](https://mlsanity.com/moe/moe-large-language-models/)

## Builds on (most cited first, 22 of 22)

- [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)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [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)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [Know What You Don't Know: Unanswerable Questions for SQuAD](https://mlsanity.com/paper/1806.03822/) (2018)
- [Get To The Point: Summarization with Pointer-Generator Networks](https://mlsanity.com/paper/1704.04368/) (2017)
- [Generating Sentences from a Continuous Space](https://mlsanity.com/paper/1511.06349/) (2015)
- [Evaluation of Text Generation: A Survey](https://mlsanity.com/paper/2006.14799/) (2020)
- [Unsupervised Question Decomposition for Question Answering](https://mlsanity.com/paper/2002.09758/) (2020)
- [Neural Question Generation from Text: A Preliminary Study](https://mlsanity.com/paper/1704.01792/) (2017)
- [A causal view of compositional zero-shot recognition](https://mlsanity.com/paper/2006.14610/) (2020)
- [Stochastic Multiple Choice Learning for Training Diverse Deep Ensembles](https://mlsanity.com/paper/1606.07839/) (2016)
- [Mixture Models for Diverse Machine Translation: Tricks of the Trade](https://mlsanity.com/paper/1902.07816/) (2019)
- [Question Answering by Reasoning Across Documents with Graph Convolutional Networks](https://mlsanity.com/paper/1808.09920/) (2018)
- [Semantic Graphs for Generating Deep Questions](https://mlsanity.com/paper/2004.12704/) (2020)
- [Mixture Content Selection for Diverse Sequence Generation](https://mlsanity.com/paper/1909.01953/) (2019)
- [Knowledge Questions from Knowledge Graphs](https://mlsanity.com/paper/1610.09935/) (2016)
- [Unsupervised Domain Adaptation of Language Models for Reading Comprehension](https://mlsanity.com/paper/1911.10768/) (2019)
- [Question Asking as Program Generation](https://mlsanity.com/paper/1711.06351/) (2017)
- [Knowledge-enriched, Type-constrained and Grammar-guided Question Generation over Knowledge Bases](https://mlsanity.com/paper/2010.03157/) (2020)

## Built on by (most cited first, 8 of 8)

- [Towards Process-Oriented, Modular, and Versatile Question Generation that Meets Educational Needs](https://mlsanity.com/paper/2205.00355/) (2022)
- [A quantitative study of NLP approaches to question difficulty estimation](https://mlsanity.com/paper/2305.10236/) (2023)
- [Beyond Flesch-Kincaid: Prompt-based Metrics Improve Difficulty Classification of Educational Texts](https://mlsanity.com/paper/2405.09482/) (2024)
- [Are You Doubtful? Oh, It Might Be Difficult Then! Exploring the Use of Model Uncertainty for Question Difficulty Estimation](https://mlsanity.com/paper/2412.11831/) (2024)
- [Reference-based Metrics Disprove Themselves in Question Generation](https://mlsanity.com/paper/2403.12242/) (2024)
- [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)
- [From Model to Classroom: Evaluating Generated MCQs for Portuguese with Narrative and Difficulty Concerns](https://mlsanity.com/paper/2506.15598/) (2025)

## Abstract (arXiv)

The ability to generate natural-language questions with controlled complexity levels is highly desirable as it further expands the applicability of question generation. In this paper, we propose an end-to-end neural complexity-controllable question generation model, which incorporates a mixture of experts (MoE) as the selector of soft templates to improve the accuracy of complexity control and the quality of generated questions. The soft templates capture question similarity while avoiding the expensive construction of actual templates. Our method introduces a novel, cross-domain complexity estimator to assess the complexity of a question, taking into account the passage, the question, the answer and their interactions. The experimental results on two benchmark QA datasets demonstrate that our QG model is superior to state-of-the-art methods in both automatic and manual evaluation. Moreover, our complexity estimator is significantly more accurate than the baselines in both in-domain and out-domain settings.