# Open-domain clarification question generation without question examples

arXiv: https://arxiv.org/abs/2110.09779 · HTML: https://mlsanity.com/paper/2110.09779/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 20 references that are in the map.
- First posted on arXiv 19 Oct 2021.

## Builds on (most cited first, 12 of 12)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Multilingual Constituency Parsing with Self-Attention and Pre-Training](https://mlsanity.com/paper/1812.11760/) (2018)
- [Learning to Ask Good Questions: Ranking Clarification Questions using Neural Expected Value of Perfect Information](https://mlsanity.com/paper/1805.04655/) (2018)
- [GuessWhat?! Visual object discovery through multi-modal dialogue](https://mlsanity.com/paper/1611.08481/) (2016)
- [Learning Cooperative Visual Dialog Agents with Deep Reinforcement Learning](https://mlsanity.com/paper/1703.06585/) (2017)
- [ShapeWorld - A new test methodology for multimodal language understanding](https://mlsanity.com/paper/1704.04517/) (2017)
- [ClarQ: A large-scale and diverse dataset for Clarification Question Generation](https://mlsanity.com/paper/2006.05986/) (2020)
- [Learning by Asking Questions](https://mlsanity.com/paper/1712.01238/) (2017)
- [Interactive Classification by Asking Informative Questions](https://mlsanity.com/paper/1911.03598/) (2019)
- [Question Asking as Program Generation](https://mlsanity.com/paper/1711.06351/) (2017)
- [Answerer in Questioner's Mind: Information Theoretic Approach to Goal-Oriented Visual Dialog](https://mlsanity.com/paper/1802.03881/) (2018)
- [Modeling question asking using neural program generation](https://mlsanity.com/paper/1907.09899/) (2019)

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

- [Polos: Multimodal Metric Learning from Human Feedback for Image Captioning](https://mlsanity.com/paper/2402.18091/) (2024)
- [ClarifyDelphi: Reinforced Clarification Questions with Defeasibility Rewards for Social and Moral Situations](https://mlsanity.com/paper/2212.10409/) (2022)
- [Improving Grounded Language Understanding in a Collaborative Environment by Interacting with Agents Through Help Feedback](https://mlsanity.com/paper/2304.10750/) (2023)
- [ChatShop: Interactive Information Seeking with Language Agents](https://mlsanity.com/paper/2404.09911/) (2024)
- [A Survey of Conversational Search](https://mlsanity.com/paper/2410.15576/) (2024)
- [CLARINET: Augmenting Language Models to Ask Clarification Questions for Retrieval](https://mlsanity.com/paper/2405.15784/) (2024)
- [Zero-shot Clarifying Question Generation for Conversational Search](https://mlsanity.com/paper/2301.12660/) (2023)
- [Contextualized Evaluations: Judging Language Model Responses to Underspecified Queries](https://mlsanity.com/paper/2411.07237/) (2024)
- [Database Search Results Disambiguation for Task-Oriented Dialog Systems](https://mlsanity.com/paper/2112.08351/) (2021)
- [JaSPICE: Automatic Evaluation Metric Using Predicate-Argument Structures for Image Captioning Models](https://mlsanity.com/paper/2311.04192/) (2023)
- [Asking More Informative Questions for Grounded Retrieval](https://mlsanity.com/paper/2311.08584/) (2023)
- [I Could've Asked That: Reformulating Unanswerable Questions](https://mlsanity.com/paper/2407.17469/) (2024)
- [Symbolic Planning and Code Generation for Grounded Dialogue](https://mlsanity.com/paper/2310.17140/) (2023)
- [DRPG (Decompose, Retrieve, Plan, Generate): An Agentic Framework for Academic Rebuttal](https://mlsanity.com/paper/2601.18081/) (2026)
- [Switching to Discriminative Image Captioning by Relieving a Bottleneck of Reinforcement Learning](https://mlsanity.com/paper/2212.03230/) (2022)
- [The Knowledge Alignment Problem: Bridging Human and External Knowledge for Large Language Models](https://mlsanity.com/paper/2305.13669/) (2023)
- [Rescue Conversations from Dead-ends: Efficient Exploration for Task-oriented Dialogue Policy Optimization](https://mlsanity.com/paper/2305.03262/) (2023)
- [How2: How to learn from procedural How-to questions](https://mlsanity.com/paper/2510.11144/) (2025)
- [Sherlock Your Queries: Learning to Ask the Right Questions for Dialogue-Based Retrieval](https://mlsanity.com/paper/2510.18659/) (2025)
- [Which Questions Improve Learning the Most? Utility Estimation of Questions with LM-based Simulations](https://mlsanity.com/paper/2502.17383/) (2025)

## Abstract (arXiv)

An overarching goal of natural language processing is to enable machines to communicate seamlessly with humans. However, natural language can be ambiguous or unclear. In cases of uncertainty, humans engage in an interactive process known as repair: asking questions and seeking clarification until their uncertainty is resolved. We propose a framework for building a visually grounded question-asking model capable of producing polar (yes-no) clarification questions to resolve misunderstandings in dialogue. Our model uses an expected information gain objective to derive informative questions from an off-the-shelf image captioner without requiring any supervised question-answer data. We demonstrate our model's ability to pose questions that improve communicative success in a goal-oriented 20 questions game with synthetic and human answerers.