Automatic Multiple Choice Question Generation From Text: A Survey
The DOI matches its Crossref record; 100 of the 106 references it cites were found in a registry or an index.
Abstract
Automatic multiple choice question (MCQ) generation from a text is a popular research area. MCQs are widely accepted for large-scale assessment in various domains and applications. However, manual generation of MCQs is expensive and time-consuming. Therefore, researchers have been attracted toward automatic MCQ generation since the late 90's. Since then, many systems have been developed for MCQ generation. We perform a systematic review of those systems. This paper presents our findings on the review. We outline a generic workflow for an automatic MCQ generation system. The workflow consists of six phases. For each of these phases, we find and discuss the list of techniques adopted in the literature. We also study the evaluation techniques for assessing the quality of the system generated MCQs. Finally, we identify the areas where the current research focus should be directed toward enriching the literature.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Additionally, while existing systems rely on textual context to generate reading-comprehension-like questions, [4, 30] we focus on generating a question well-aligned with the provided LO, allowing for easier large-scale evaluation.”
From A Comparative Study of AI-Generated (GPT-4) and Human-crafted MCQs in Programming Education (2024) · cites this paper as [4]
Citations
Cites
Efficient Estimation of Word Representations in Vector Space
Mikolov, T., Chen, K., Corrado, G., & Dean, J. (2013) · arXiv · doi:10.48550/arxiv.1301.3781 · Cited by 26,568 · cited 1×
“Kumar, Banchs, and D’Haro [46] selected the distractors using semantic similarity computed through the word2vec tool [110].”
MethodAn introduction to latent semantic analysis
Landauer, T. K., Foltz, P. W., & Laham, D. (1998) · Discourse Processes · doi:10.1080/01638539809545028 · Cited by 4,880 · cited 1×
“Aldabe and Maritxalar [27] used Latent Semantic Analysis [108] to generate distractors.”
MethodIntroduction to WordNet: An On-line Lexical Database*
Miller, G. A., Beckwith, R., Fellbaum, C., Gross, D., & Miller, K. J. (1990) · International Journal of Lexicography · doi:10.1093/ijl/3.4.235 · Cited by 4,197 · cited 1×
“WordNet: WordNet [105] is a lexical database that groups the words into sets of synonyms (called synsets), and records the relations among these synonym sets or their members.”
BackgroundJurafsky, D. S., & Martin, J. (2000) · Cited by 4,132
Automatic Labeling of Semantic Roles
Gildea, D., & Jurafsky, D. (2002) · Computational Linguistics · doi:10.1162/089120102760275983 · Cited by 1,626
Information filtering and information retrieval: two sides of the same coin?
Belkin, N. J., & Croft, W. B. (1992) · Communications of the ACM · doi:10.1145/138859.138861 · Cited by 1,308
Antoniou, G., & van Harmelen, F. (2004) · Handbook on Ontologies · doi:10.1007/978-3-540-24750-0_4 · Cited by 1,017
Interpreting TF-IDF term weights as making relevance decisions
Wu, H. C., Luk, R. W. P., Wong, K. F., & Kwok, K. L. (2008) · ACM Transactions on Information Systems · doi:10.1145/1361684.1361686 · Cited by 821 · cited 1×
“Statistical Analysis: Several systems used certain word level analysis including word frequency, n-gram frequency, Term frequency * inverse document frequency (Tf*Idf) [85], and co-occurrence statistics in various modules ([1], [6], [14], [16], [47], [49], [69], [76], [77], [86], [87], [88]).”
MethodStanford’s Multi-Pass Sieve Coreference Resolution System at the CoNLL-2011 Shared Task
Lee, H., Peirsman, Y., Chang, A. L. S., Chambers, N., Surdeanu, M., & Jurafsky, D. (2011) · Lirias · Cited by 504
Using WordNet Based Context Vectors to Estimate the Semantic Relatedness of Concepts
Patwardhan, S., & Pedersen, T. (2006) · Cited by 375
Research works printed but not linked: 11
- hoshino, 2010, Predicting the difficulty of multiple-choice close questions for computer-adaptive testing, Proc CICLing, 279
- correia, 2010, Automatic generation of cloze question distractors, Proc Interspeech Satellite Workshop 2nd Lang Stud Acquisition Learn Edu Technol, 1
- stancheva, 2017, A model for generation of test questions, Comptes Rendus de L'Academie Bulgare des Sciences, 70, 619
- bhale, 0, Automatic question generation using Wikipedia, Imperial Journal of Interdisciplinary Research (IJIR), 2, 943
- agarwal, 2012, Cloze and open cloze question generation systems and their evaluation guidelines, MS Thesis IIIT Hyderabad Hyderabad INDIA
- pino, 2008, A selection strategy to improve cloze question quality, Proc Workshop Intell Tutoring Syst Ill-Defined Domains 9th Int Conf Intell Tutoring Syst, 22
- kojiri, 2010, Statistical learning-based approach for automatic generation system of multiple-choice cloze questions, Proc Workshop Proc 18th Int Conf Comput Edu
- sung, 2007, The design of automatic quiz generation for ubiquitous English e-learning system, Proc Conf Technol Enhanced Learn, 161
- nielsen, 2008, A taxonomy of questions for question generation, Workshop on the Question Generation Shared Task and Evaluation Challenge, 15
- goto, 2009, An automatic generation of multiple-choice cloze questions based on statistical learning, Proc 17th Int Conf Comput Edu, 415
- lin, 2007, An automatic multiple-choice question generation scheme for English adjective understanding, Proc Workshop Model Manage Gener Problems/Questions eLearn 15th Int Conf Comput Edu, 137
Cited by
A Systematic Review of Automatic Question Generation for Educational Purposes
Kurdi, G., Leo, J., Parsia, B., Sattler, U., & Al-Emari, S. (2020) · International Journal of Artificial Intelligence in Education · doi:10.1007/s40593-019-00186-y · Cited by 514
Diwan, C., Srinivasa, S., Suri, G., Agarwal, S., & Ram, P. (2023) · Computers and Education: Artificial Intelligence · doi:10.1016/j.caeai.2022.100110 · Cited by 106
A Comparative Study of AI-Generated (GPT-4) and Human-crafted MCQs in Programming Education
Doughty, J., Wan, Z., Bompelli, A., Qayum, J., Wang, T., Zhang, J., Zheng, Y., Doyle, A., Sridhar, P., Agarwal, A., et al. (2024) · Proceedings of the 26th Australasian Computing Education Conference · doi:10.1145/3636243.3636256 · Cited by 132
“Note that some of the LOs extracted from the courses were not well-defined (e.g., no action verb) and, hence, it was not possible to categorize them in terms of Bloom’s taxonomy.”
BackgroundMCQGen: A Large Language Model-Driven MCQ Generator for Personalized Learning
Hang, C. N., Tan, C. W., & Yu, P.-D. (2024) · IEEE Access · doi:10.1109/access.2024.3420709 · Cited by 151
“Research on automatic MCQ generation began over two decades ago, and since then, a significant amount of effort has been dedicated to its development [5].”
BackgroundAutomatic question generation and answer assessment: a survey
Das, B., Majumder, M., Phadikar, S., & Sekh, A. A. (2021) · Research and Practice in Technology Enhanced Learning · doi:10.1186/s41039-021-00151-1 · Cited by 123
Metadata
- Authors
- CH, D. R., & Saha, S. K.
- Affiliations
- Birla Institute of Technology, Mesra (IN)
- Venue
- IEEE Transactions on Learning Technologies
- Published
- 2020-01-01
- Volume
- 13
- Issue
- 1
- Pages
- 14-25
- ISSN
- 1939-1382 (ISSN-L)
- 2372-0050
- OpenAlex
- W2906432682
- Cited by
- 144
- References
- 106
- Citations by year
- 2026: 15 · 2025: 29 · 2024: 29 · 2023: 25 · 2022: 20 · 2021: 17 · 2020: 8
- FWCI
- 3.64
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- Locations
- IEEE Transactions on Learning Technologies (publishedVersion)
- Funders
- Science and Engineering Research Board (YSS/2015/001948)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Information Systems › Educational Technology and Assessment
- Keywords
- large-scale assessment, automated assessment
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Automatic Multiple Choice Question Generation From Text: A Survey. https://app.cochat.ai/papers/10.1109/tlt.2018.2889100
- The paper
- CH, D. R., & Saha, S. K. (2020). Automatic Multiple Choice Question Generation From Text: A Survey. IEEE Transactions on Learning Technologies. https://doi.org/10.1109/tlt.2018.2889100
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.