CONSISTENT: Open-Ended Question Generation From News Articles
Not on the map. Why?
Abstract (arXiv)
Recent work on question generation has largely focused on factoid questions such as who, what, where, when about basic facts. Generating open-ended why, how, what, etc. questions that require long-form answers have proven more difficult. To facilitate the generation of open-ended questions, we propose CONSISTENT, a new end-to-end system for generating open-ended questions that are answerable from and faithful to the input text. Using news articles as a trustworthy foundation for experimentation, we demonstrate our model's strength over several baselines using both automatic and human=based evaluations. We contribute an evaluation dataset of expert-generated open-ended questions.We discuss potential downstream applications for news media organizations.
Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 34 of its 49 references that are in the map. First posted on arXiv 20 Oct 2022.
Builds on
34 of 49 references.
References · 34
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
- 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
- 2019BERTScore: Evaluating Text Generation with BERTcited by 5,462
- 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,115
- 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,895
- 2018Know What You Don't Know: Unanswerable Questions for SQuADcited by 1,538
- 2021Multitask Prompted Training Enables Zero-Shot Task Generalizationcited by 1,462
- 2018Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarizationcited by 1,308
- 2020BLEURT: Learning Robust Metrics for Text Generationcited by 1,196
- 2018Hierarchical Neural Story Generationcited by 1,182
- 2019CTRL: A Conditional Transformer Language Model for Controllable Generationcited by 754
- 2018CoQA: A Conversational Question Answering Challengecited by 674
22 more
- 2019ELI5: Long Form Question Answeringcited by 567
- 2019The Woman Worked as a Babysitter: On Biases in Language Generationcited by 540
- 2018QuAC : Question Answering in Contextcited by 379
- 2021LongT5: Efficient Text-To-Text Transformer for Long Sequencescited by 232
- 2021Societal Biases in Language Generation: Progress and Challengescited by 201
- 2021PAQ: 65 Million Probably-Asked Questions and What You Can Do With Themcited by 198
- 2017Learning to Ask: Neural Question Generation for Reading Comprehensioncited by 186
- 2021Hurdles to Progress in Long-form Question Answeringcited by 166
- 2019Synthetic QA Corpora Generation with Roundtrip Consistencycited by 143
- 2018Learning to Ask Good Questions: Ranking Clarification Questions using Neural Expected Value of Perfect Informationcited by 110
- 2021The Perils of Using Mechanical Turk to Evaluate Open-Ended Text Generationcited by 96
- 2019Answer-based Adversarial Training for Generating Clarification Questionscited by 42
- 2021Ask what's missing and what's useful: Improving Clarification Question Generation using Global Knowledgecited by 40
- 2020Unsupervised Multi-hop Question Answering by Question Generationcited by 38
- 2021Controllable Open-ended Question Generation with A New Question Type Ontologycited by 36
- 2020Inquisitive Question Generation for High Level Text Comprehensioncited by 31
- 2019Improving Question Generation With to the Point Contextcited by 15
- 2019Ask to Learn: A Study on Curiosity-driven Question Generationcited by 15
- 2022Quiz Design Task: Helping Teachers Create Quizzes with Automated Question Generationcited by 12
- 2020Accelerating Real-Time Question Answering via Question Generationcited by 11
- 2022"What makes a question inquisitive?" A Study on Type-Controlled Inquisitive Question Generationcited by 7
- 2022NewsPod: Automatic and Interactive News Podcastscited by 6
Built on by
Citing papers per year: 2022: 1; 2023: 3; 2024: 1; 2025: 1.
6 papers.
- 2023QUDEVAL: The Evaluation of Questions Under Discussion Discourse Parsingcited by 19
- 2022Socratic Pretraining: Question-Driven Pretraining for Controllable Summarizationcited by 17
- 2023Exploring the Viability of Synthetic Query Generation for Relevance Predictioncited by 9
- 2023Evaluation of Question Generation Needs More Referencescited by 8
- 2025From Superficial to Deep: Integrating External Knowledge for Follow-up Question Generation Using Knowledge Graph and LLMcited by 2
- 2024NewsQs: Multi-Source Question Generation for the Inquiring Mindcited by 0
- 2025From Superficial to Deep: Integrating External Knowledge for Follow-up Question Generation Using Knowledge Graph and LLM8 Apr 2025
- 2024NewsQs: Multi-Source Question Generation for the Inquiring Mind28 Feb 2024
- 2023QUDEVAL: The Evaluation of Questions Under Discussion Discourse Parsing23 Oct 2023
- 2023Evaluation of Question Generation Needs More References26 May 2023
- 2023Exploring the Viability of Synthetic Query Generation for Relevance Prediction19 May 2023
- 2022Socratic Pretraining: Question-Driven Pretraining for Controllable Summarization20 Dec 2022