Difficulty-Controllable Cloze Question Distractor Generation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916026744045568 |
|---|---|
| author | Kang, Seokhoon Jeon, Yejin Hwang, Seonjeong Lee, Gary Geunbae |
| author_facet | Kang, Seokhoon Jeon, Yejin Hwang, Seonjeong Lee, Gary Geunbae |
| contents | Multiple-choice cloze questions are commonly used to assess linguistic proficiency and comprehension. However, generating high-quality distractors remains challenging, as existing methods often lack adaptability and control over difficulty levels, and the absence of difficulty-annotated datasets further hinders progress. To address these issues, we propose a novel framework for generating distractors with controllable difficulty by leveraging both data augmentation and a multitask learning strategy. First, to create a high-quality, difficulty-annotated dataset, we introduce a two-way distractor generation process to produce diverse and plausible distractors. These candidates are filtered and then categorized by difficulty using an ensemble QA system. Second, this newly created dataset is used to train a difficulty-controllable generation model via multitask learning. Experimental results demonstrate that our method generates high-quality distractors across difficulty levels and substantially outperforms GPT-4o in aligning distractor difficulty with human perception. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_01526 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Difficulty-Controllable Cloze Question Distractor Generation Kang, Seokhoon Jeon, Yejin Hwang, Seonjeong Lee, Gary Geunbae Computation and Language Multiple-choice cloze questions are commonly used to assess linguistic proficiency and comprehension. However, generating high-quality distractors remains challenging, as existing methods often lack adaptability and control over difficulty levels, and the absence of difficulty-annotated datasets further hinders progress. To address these issues, we propose a novel framework for generating distractors with controllable difficulty by leveraging both data augmentation and a multitask learning strategy. First, to create a high-quality, difficulty-annotated dataset, we introduce a two-way distractor generation process to produce diverse and plausible distractors. These candidates are filtered and then categorized by difficulty using an ensemble QA system. Second, this newly created dataset is used to train a difficulty-controllable generation model via multitask learning. Experimental results demonstrate that our method generates high-quality distractors across difficulty levels and substantially outperforms GPT-4o in aligning distractor difficulty with human perception. |
| title | Difficulty-Controllable Cloze Question Distractor Generation |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2511.01526 |