# Generating Question-Answer Hierarchies

arXiv: https://arxiv.org/abs/1906.02622 · HTML: https://mlsanity.com/paper/1906.02622/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Jun 2019.

## Built on by (most cited first, 20 of 20)

- [Controllable Open-ended Question Generation with A New Question Type Ontology](https://mlsanity.com/paper/2107.00152/) (2021)
- [Educational Question Generation of Children Storybooks via Question Type Distribution Learning and Event-Centric Summarization](https://mlsanity.com/paper/2203.14187/) (2022)
- [HIBRIDS: Attention with Hierarchical Biases for Structure-aware Long Document Summarization](https://mlsanity.com/paper/2203.10741/) (2022)
- [QUDEVAL: The Evaluation of Questions Under Discussion Discourse Parsing](https://mlsanity.com/paper/2310.14520/) (2023)
- [What's The Latest? A Question-driven News Chatbot](https://mlsanity.com/paper/2105.05392/) (2021)
- [Leaf: Multiple-Choice Question Generation](https://mlsanity.com/paper/2201.09012/) (2022)
- [OneStop QAMaker: Extract Question-Answer Pairs from Text in a One-Stop Approach](https://mlsanity.com/paper/2102.12128/) (2021)
- [Paired Examples as Indirect Supervision in Latent Decision Models](https://mlsanity.com/paper/2104.01759/) (2021)
- [To Adapt or to Annotate: Challenges and Interventions for Domain Adaptation in Open-Domain Question Answering](https://mlsanity.com/paper/2212.10381/) (2022)
- [AnswerQuest: A System for Generating Question-Answer Items from Multi-Paragraph Documents](https://mlsanity.com/paper/2103.03820/) (2021)
- [Asking Questions Like Educational Experts: Automatically Generating Question-Answer Pairs on Real-World Examination Data](https://mlsanity.com/paper/2109.05179/) (2021)
- [Indian Legal NLP Benchmarks : A Survey](https://mlsanity.com/paper/2107.06056/) (2021)
- [Generating Self-Contained and Summary-Centric Question Answer Pairs via Differentiable Reward Imitation Learning](https://mlsanity.com/paper/2109.04689/) (2021)
- [New Methods & Metrics for LFQA tasks](https://mlsanity.com/paper/2112.13432/) (2021)
- [Unified Question Generation with Continual Lifelong Learning](https://mlsanity.com/paper/2201.09696/) (2022)
- [PREME: Preference-based Meeting Exploration through an Interactive Questionnaire](https://mlsanity.com/paper/2205.02370/) (2022)
- [Consecutive Question Generation via Dynamic Multitask Learning](https://mlsanity.com/paper/2211.08850/) (2022)
- [DoGMaTiQ: Automated Generation of Question-and-Answer Nuggets for Report Evaluation](https://mlsanity.com/paper/2605.04458/) (2026)
- [A Comparative and Experimental Study on Automatic Question Answering Systems and its Robustness against Word Jumbling](https://mlsanity.com/paper/2311.15513/) (2023)
- [Backprompting: Leveraging Synthetic Production Data for Health Advice Guardrails](https://mlsanity.com/paper/2508.18384/) (2025)

## Abstract (arXiv)

The process of knowledge acquisition can be viewed as a question-answer game between a student and a teacher in which the student typically starts by asking broad, open-ended questions before drilling down into specifics (Hintikka, 1981; Hakkarainen and Sintonen, 2002). This pedagogical perspective motivates a new way of representing documents. In this paper, we present SQUASH (Specificity-controlled Question-Answer Hierarchies), a novel and challenging text generation task that converts an input document into a hierarchy of question-answer pairs. Users can click on high-level questions (e.g., "Why did Frodo leave the Fellowship?") to reveal related but more specific questions (e.g., "Who did Frodo leave with?"). Using a question taxonomy loosely based on Lehnert (1978), we classify questions in existing reading comprehension datasets as either "general" or "specific". We then use these labels as input to a pipelined system centered around a conditional neural language model. We extensively evaluate the quality of the generated QA hierarchies through crowdsourced experiments and report strong empirical results.