Distractor Generation
13 papers with code • 1 benchmarks • 2 datasets
Given a passage, a question, and an answer phrase, the goal of distractor generation (DG) is to generate context-related wrong options (i.e., distractor) for multiple-choice questions (MCQ).
RACE
SciQ
Latest papers
Exploring Automated Distractor Generation for Math Multiple-choice Questions via Large Language Models
umass-ml4ed/prompt_distractor_generation_naacl
•
•
Multiple-choice questions (MCQs) are ubiquitous in almost all levels of education since they are easy to administer, grade, and are a reliable format in assessments and practices.
CDGP: Automatic Cloze Distractor Generation based on Pre-trained Language Model
Manually designing cloze test consumes enormous time and efforts.
A Novel Multi-Stage Prompting Approach for Language Agnostic MCQ Generation using GPT
We introduce a multi-stage prompting approach (MSP) for the generation of multiple choice questions (MCQs), harnessing the capabilities of GPT models such as text-davinci-003 and GPT-4, renowned for their excellence across various NLP tasks.
BRAINTEASER: Lateral Thinking Puzzles for Large Language Models
giannispana/ails-ntua-at-semeval-2024-task-9-brainteaser
•
•
The success of language models has inspired the NLP community to attend to tasks that require implicit and complex reasoning, relying on human-like commonsense mechanisms.
Distractor generation for multiple-choice questions with predictive prompting and large language models
We also show the gains of our approach 1 in generating high-quality distractors by comparing it with a zero-shot ChatGPT and a few-shot ChatGPT prompted with static examples.
EduQG: A Multi-format Multiple Choice Dataset for the Educational Domain
hadifar/question-generation
•
•
Thus, our versatile dataset can be used for both question and distractor generation, as well as to explore new challenges such as question format conversion.
BERT-based distractor generation for Swedish reading comprehension questions using a small-scale dataset
dkalpakchi/swequad-mc
•
•
INLG (ACL) 2021
An important part when constructing multiple-choice questions (MCQs) for reading comprehension assessment are the distractors, the incorrect but preferably plausible answer options.
ZmBART: An Unsupervised Cross-lingual Transfer Framework for Language Generation
kaushal0494/ZmBART
•
•
Findings (ACL) 2021
In this framework, we further pre-train mBART sequence-to-sequence denoising auto-encoder model with an auxiliary task using monolingual data of three languages.
Quiz-Style Question Generation for News Stories
As a first step towards measuring news informedness at a scale, we study the problem of quiz-style multiple-choice question generation, which may be used to survey users about their knowledge of recent news.
A BERT-based Distractor Generation Scheme with Multi-tasking and Negative Answer Training Strategies.
voidful/BDG
•
•
Findings of the Association for Computational Linguistics 2020
In this paper, we investigate the following two limitations for the existing distractor generation (DG) methods.
