# Co-Attention Hierarchical Network: Generating Coherent Long Distractors for Reading Comprehension

arXiv: https://arxiv.org/abs/1911.08648 · HTML: https://mlsanity.com/paper/1911.08648/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Nov 2019.

## Built on by (most cited first, 14 of 14)

- [A Comparative Study of AI-Generated (GPT-4) and Human-crafted MCQs in Programming Education](https://mlsanity.com/paper/2312.03173/) (2023)
- [Distractor Generation in Multiple-Choice Tasks: A Survey of Methods, Datasets, and Evaluation](https://mlsanity.com/paper/2402.01512/) (2024)
- [On the Robustness of Reading Comprehension Models to Entity Renaming](https://mlsanity.com/paper/2110.08555/) (2021)
- [Distractor generation for multiple-choice questions with predictive prompting and large language models](https://mlsanity.com/paper/2307.16338/) (2023)
- [BERT-based distractor generation for Swedish reading comprehension questions using a small-scale dataset](https://mlsanity.com/paper/2108.03973/) (2021)
- [Unsupervised Distractor Generation via Large Language Model Distilling and Counterfactual Contrastive Decoding](https://mlsanity.com/paper/2406.01306/) (2024)
- [DISTO: Evaluating Textual Distractors for Multi-Choice Questions using Negative Sampling based Approach](https://mlsanity.com/paper/2304.04881/) (2023)
- [D-GEN: Automatic Distractor Generation and Evaluation for Reliable Assessment of Generative Model](https://mlsanity.com/paper/2504.13439/) (2025)
- [EMBRACE: Evaluation and Modifications for Boosting RACE](https://mlsanity.com/paper/2305.08433/) (2023)
- [AGent: A Novel Pipeline for Automatically Creating Unanswerable Questions](https://mlsanity.com/paper/2309.05103/) (2023)
- [DGRC: An Effective Fine-tuning Framework for Distractor Generation in Chinese Multi-choice Reading Comprehension](https://mlsanity.com/paper/2405.19139/) (2024)
- [Harnessing Structured Knowledge: A Concept Map-Based Approach for High-Quality Multiple Choice Question Generation with Effective Distractors](https://mlsanity.com/paper/2505.02850/) (2025)
- [From Model to Classroom: Evaluating Generated MCQs for Portuguese with Narrative and Difficulty Concerns](https://mlsanity.com/paper/2506.15598/) (2025)
- [FarsiMCQGen: a Persian Multiple-choice Question Generation Framework](https://mlsanity.com/paper/2510.15134/) (2025)

## Abstract (arXiv)

In reading comprehension, generating sentence-level distractors is a significant task, which requires a deep understanding of the article and question. The traditional entity-centered methods can only generate word-level or phrase-level distractors. Although recently proposed neural-based methods like sequence-to-sequence (Seq2Seq) model show great potential in generating creative text, the previous neural methods for distractor generation ignore two important aspects. First, they didn't model the interactions between the article and question, making the generated distractors tend to be too general or not relevant to question context. Second, they didn't emphasize the relationship between the distractor and article, making the generated distractors not semantically relevant to the article and thus fail to form a set of meaningful options. To solve the first problem, we propose a co-attention enhanced hierarchical architecture to better capture the interactions between the article and question, thus guide the decoder to generate more coherent distractors. To alleviate the second problem, we add an additional semantic similarity loss to push the generated distractors more relevant to the article. Experimental results show that our model outperforms several strong baselines on automatic metrics, achieving state-of-the-art performance. Further human evaluation indicates that our generated distractors are more coherent and more educative compared with those distractors generated by baselines.