EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Review of Neural Question Generation: Approaches, Challenges, and Future Directions

Shasha Guo, Liang Pang, Jing Zhang, Cuiping Li, Hong Chen

ACM Computing Surveys · 31.01.2027 · 59 (1) · 1-37

DOI: 10.1145/3843765 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Computing Surveys, online erschienen am 29.10.2026. Verfasst von Shasha Guo und 4 weiteren Autor:innen. Die Arbeit nennt 180 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Strategic Priority Research Program of the CAS, National Key Research & Develop Plan, Key Research and Development Program of Xinjiang Uyghur Autonomous Region.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The goal of question generation is to automatically produce relevant and meaningful questions from diverse inputs such as knowledge bases, natural language texts, and images. With the rapid advancement of neural architectures, neural question generation (NQG) has attracted growing attention across both academia and industry. In this survey, we provide a comprehensive review of developments in NQG, spanning traditional neural approaches to the latest paradigms driven by large language models (LLMs) and multimodal large language models (MLLMs). We begin by outlining the fundamental components of NQG, including its problem formulation, benchmark datasets, evaluation metrics, and representative applications. Next, we categorize existing methods into three main types: structured NQG , which relies on structured data sources; unstructured NQG , which handles loosely structured inputs such as texts or images; and hybrid NQG , which integrates multiple modalities. For each category, we review representative neural models and synthesize the problems addressed by successive generations of methods, their remaining limitations, and the motivations behind major methodological transitions. Furthermore, we trace the progression of NQG from supervised neural approaches and pre-trained models to prompting, retrieval-augmented generation, reinforcement learning, and emerging tool-augmented and agent-based paradigms. We also discuss how recent LLMs and MLLMs have enabled more contextually aligned, knowledge-grounded, and reasoning-enhanced question generation, together with emerging concerns such as hallucination, bias, and evaluation reliability. Finally, we outline open challenges and emerging research trends, offering a forward-looking perspective on the evolution of NQG. This survey presents a meticulously curated compilation of related papers, datasets, and code, 1 serving as a comprehensive resource for anyone studying NQG.

Förderung

  • Strategic Priority Research Program of the CAS
  • National Key Research & Develop Plan
  • Key Research and Development Program of Xinjiang Uyghur Autonomous Region
  • National Natural Science Foundation of China
  • Beijing Nova Program
  • Youth Innovation Promotion Association CAS

Zitieren

APA

Guo, S., Pang, L., Zhang, J., Li, C., & Chen, H. (2027). A Review of Neural Question Generation: Approaches, Challenges, and Future Directions. ACM Computing Surveys, 59(1), 1-37. https://doi.org/10.1145/3843765

Vancouver

Guo S, Pang L, Zhang J, Li C, Chen H. A Review of Neural Question Generation: Approaches, Challenges, and Future Directions. ACM Computing Surveys. 2027;59(1):1-37. doi:10.1145/3843765

BibTeX
@article{Guo2027,
  author = {Guo, Shasha and Pang, Liang and Zhang, Jing and Li, Cuiping and Chen, Hong},
  title = {A Review of Neural Question Generation: Approaches, Challenges, and Future Directions},
  journal = {ACM Computing Surveys},
  year = {2027},
  volume = {59},
  number = {1},
  pages = {1--37},
  doi = {10.1145/3843765}
}
Kostenlos starten →