Challenge: Existing methods for generating high-quality distractors lack adaptability and control over difficulty levels.
Approach: They propose a two-way distractor generation process to generate plausible distractors using an ensemble QA system and a multitask learning strategy to train a difficulty-controllable generation model.
Outcome: The proposed method significantly outperforms GPT-4o in aligning distractor difficulty with human perception.

Similar Papers

Distractor Generation in Multiple-Choice Tasks: A Survey of Methods, Datasets, and Evaluation (2024.emnlp-main)

Copied to clipboard

Challenge: Objective questions such as fill-in-the-blank and multiple-choice require examinees to select one valid answer from a set of invalid options.
Approach: They examine distractor generation tasks, datasets, methods, and evaluation metrics for English objective questions.
Outcome: The proposed task is based on fill-in-the-blank and multiple choice questions and is widely utilized in educational settings across various domains and subjects.
Exploring Automated Distractor Generation for Math Multiple-choice Questions via Large Language Models (2024.findings-naacl)

Copied to clipboard

Challenge: Multiple-choice questions (MCQs) are easy to administer and grade . but crafting high-quality distractors remains labor-intensive and limited scalability .
Approach: They propose to automate the generation of distractors in math MCQs by using large language models to generate distractors.
Outcome: The proposed methods can generate valid distractors, but they are less adept at anticipating common errors or misconceptions among real students.
Automatic Distractor Generation for Multiple Choice Questions in Standard Tests (2020.coling-main)

Copied to clipboard

Challenge: Existing methods to generate distractors for multiple choice questions are expensive and time-consuming.
Approach: They propose a question and answer guided distractor generation framework to automate distractors generated by domain experts.
Outcome: The proposed model outperforms existing models and achieves state-of-the-art on a large-scale dataset.
CDGP: Automatic Cloze Distractor Generation based on Pre-trained Language Model (2022.findings-emnlp)

Copied to clipboard

Challenge: Existing approaches to generate cloze distractors with carefully-designed distractors are limited due to wrong option selection.
Approach: They propose to employ pre-trained language models as an alternative to cloze distractor generation by using pre-designed distractors.
Outcome: The proposed model improves the state-of-the-art cloze test score from 14.94 to 34.17 (NDCG@10) The proposed framework improves clozing distractors by incorporating pre-trained language models.
CrossQG: Improving Difficulty-Controllable Question Generation through Consistency Enhancement (2025.findings-emnlp)

Copied to clipboard

Challenge: Large language models can generate questions with controlled difficulty, but they often fail to align with the given target difficulty.
Approach: They propose a question generation method that requires no tuning of generator parameters yet significantly improves difficulty consistency.
Outcome: The proposed method outperforms several mainstream methods on high-quality question answering datasets and achieves superior consistency with target difficulty.
Distractor Generation Using Generative and Discriminative Capabilities of Transformer-based Models (2024.lrec-main)

Copied to clipboard

Challenge: Multiple Choice Questions (MCQs) are used to test language learners' comprehension and knowledge.
Approach: They propose an automatic distractor generation approach which generates correct and incorrect answer options and then discriminates potential correct options from distractors.
Outcome: The proposed approach outperforms previous models on multiple choice questions and reading comprehension questions.
Distractor Generation based on Text2Text Language Models with Pseudo Kullback-Leibler Divergence Regulation (2023.findings-acl)

Copied to clipboard

Challenge: Existing methods for cloze-style multiple choice questions (MCQs) distractor generation are based on knowledge bases and pre-trained language models.
Approach: They propose to formulate cloze distractor generation task as Text2Text task and propose a pseudo Kullback-Leibler divergence for regulating the generation to consider item discrimination index in education evaluation.
Outcome: The proposed model improves state-of-the-art performance from 10.81 to 22.00 (p@1 score)
Guiding the Growth: Difficulty-Controllable Question Generation through Step-by-Step Rewriting (2021.acl-long)

Copied to clipboard

Challenge: Existing QG systems perform substantially worse in answering multi-hop questions than single-hop ones.
Approach: They propose a framework that progressively increases question difficulty through step-by-step rewriting under the guidance of an extracted reasoning chain.
Outcome: The proposed framework increases question difficulty through step-by-step rewriting under the guidance of an extracted reasoning chain.
Fine-Tuning Encoder-Decoder Models with Contrastive Learning for In-Context Distractor Generation (2025.findings-emnlp)

Copied to clipboard

Challenge: Distractors are used to generate plausible but incorrect options for fill-in-the-blank questions . research studies focus on fine-tuning pre-trained models with data augmentation techniques to generate distractors .
Approach: They propose a model that trains the model to recognize essential semantic features necessary to generate distractors.
Outcome: The proposed model outperforms existing models on two public datasets.
DisGeM: Distractor Generation for Multiple Choice Questions with Span Masking (2024.findings-emnlp)

Copied to clipboard

Challenge: Multiple-choice cloze tests are a prevalent form of assessment that evaluates students' comprehension and inference abilities.
Approach: They propose a framework for distractor generation using readily available pre-trained language models . human evaluations confirm that their approach produces more effective distractors .
Outcome: The proposed framework outperforms existing methods without training or fine-tuning human evaluations confirm it.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations