mlsanityData to 14 Oct 2026

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

arXiv 2110.06560 ↗First posted 13 Oct 2021cs.CLcited by 8

On the map: Mixture-of-experts → MoE large language models

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.

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.

Builds on

22 of 37 references.

Closest ancestors · 1

Same direction, newest first

  1. 2017Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer23 Jan

Other references · 21

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,548
  4. 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,148
  5. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  6. 2018Know What You Don't Know: Unanswerable Questions for SQuADcited by 1,554
  7. 2017Get To The Point: Summarization with Pointer-Generator Networkscited by 1,292
  8. 2015Generating Sentences from a Continuous Spacecited by 612
  9. 2020Evaluation of Text Generation: A Surveycited by 277
  10. 2020Unsupervised Question Decomposition for Question Answeringcited by 118
  11. 2017Neural Question Generation from Text: A Preliminary Studycited by 78
  12. 2020A causal view of compositional zero-shot recognitioncited by 78
9 more
  1. 2016Stochastic Multiple Choice Learning for Training Diverse Deep Ensemblescited by 77
  2. 2019Mixture Models for Diverse Machine Translation: Tricks of the Tradecited by 77
  3. 2018Question Answering by Reasoning Across Documents with Graph Convolutional Networkscited by 56
  4. 2020Semantic Graphs for Generating Deep Questionscited by 38
  5. 2019Mixture Content Selection for Diverse Sequence Generationcited by 27
  6. 2016Knowledge Questions from Knowledge Graphscited by 15
  7. 2019Unsupervised Domain Adaptation of Language Models for Reading Comprehensioncited by 15
  8. 2017Question Asking as Program Generationcited by 13
  9. 2020Knowledge-enriched, Type-constrained and Grammar-guided Question Generation over Knowledge Basescited by 9

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 2; 2024: 3; 2025: 2.

8 papers.

  1. 2022Towards Process-Oriented, Modular, and Versatile Question Generation that Meets Educational Needscited by 19
  2. 2023A quantitative study of NLP approaches to question difficulty estimationcited by 13
  3. 2024Beyond Flesch-Kincaid: Prompt-based Metrics Improve Difficulty Classification of Educational Textscited by 9
  4. 2024Are You Doubtful? Oh, It Might Be Difficult Then! Exploring the Use of Model Uncertainty for Question Difficulty Estimationcited by 7
  5. 2024Reference-based Metrics Disprove Themselves in Question Generationcited by 3
  6. 2023SkillQG: Learning to Generate Question for Reading Comprehension Assessmentcited by 1
  7. 2025Advancing Question Generation with Joint Narrative and Difficulty Controlcited by 1
  8. 2025From Model to Classroom: Evaluating Generated MCQs for Portuguese with Narrative and Difficulty Concernscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Explainable Multi-hop Question Generation: An End-to-End Approach without Intermediate Question Labeling
  2. 2025Difficulty-Controllable Multiple-Choice Question Generation Using Large Language Models and Direct Preference Optimization
  3. 2025Generate-Then-Validate: A Novel Question Generation Approach Using Small Language Models
  4. 2023Getting MoRE out of Mixture of Language Model Reasoning Experts
  5. 2025Benchmarking Critical Questions Generation: A Challenging Reasoning Task for Large Language Models
  6. 2025ExpertGenQA: Open-ended QA generation in Specialized Domains
  7. 2024Contrastive Learning for Knowledge-Based Question Generation in Large Language Models
  8. 2025MoEMoE: Question Guided Dense and Scalable Sparse Mixture-of-Expert for Multi-source Multi-modal Answering