# Answer-based Adversarial Training for Generating Clarification Questions

arXiv: https://arxiv.org/abs/1904.02281 · HTML: https://mlsanity.com/paper/1904.02281/

## Key facts

- Cited by 43 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Apr 2019.

## Built on by (most cited first, 30 of 43)

- [Measuring and Narrowing the Compositionality Gap in Language Models](https://mlsanity.com/paper/2210.03350/) (2022)
- [Distilling Reasoning Capabilities into Smaller Language Models](https://mlsanity.com/paper/2212.00193/) (2022)
- [STaR-GATE: Teaching Language Models to Ask Clarifying Questions](https://mlsanity.com/paper/2403.19154/) (2024)
- [CLAM: Selective Clarification for Ambiguous Questions with Generative Language Models](https://mlsanity.com/paper/2212.07769/) (2022)
- [Neural Approaches to Conversational Information Retrieval](https://mlsanity.com/paper/2201.05176/) (2022)
- [Ask what's missing and what's useful: Improving Clarification Question Generation using Global Knowledge](https://mlsanity.com/paper/2104.06828/) (2021)
- [Controllable Open-ended Question Generation with A New Question Type Ontology](https://mlsanity.com/paper/2107.00152/) (2021)
- [ClarifyDelphi: Reinforced Clarification Questions with Defeasibility Rewards for Social and Moral Situations](https://mlsanity.com/paper/2212.10409/) (2022)
- [Varifocal Question Generation for Fact-checking](https://mlsanity.com/paper/2210.12400/) (2022)
- [Evaluating Mixed-initiative Conversational Search Systems via User Simulation](https://mlsanity.com/paper/2204.08046/) (2022)
- [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)
- [QUDEVAL: The Evaluation of Questions Under Discussion Discourse Parsing](https://mlsanity.com/paper/2310.14520/) (2023)
- [A Review of Text Style Transfer using Deep Learning](https://mlsanity.com/paper/2109.15144/) (2021)
- [A Survey on Medical Document Summarization](https://mlsanity.com/paper/2212.01669/) (2022)
- [Zero-shot Clarifying Question Generation for Conversational Search](https://mlsanity.com/paper/2301.12660/) (2023)
- [FOLLOWUPQG: Towards Information-Seeking Follow-up Question Generation](https://mlsanity.com/paper/2309.05007/) (2023)
- [Diverse and Specific Clarification Question Generation with Keywords](https://mlsanity.com/paper/2104.10317/) (2021)
- [Generating Usage-related Questions for Preference Elicitation in Conversational Recommender Systems](https://mlsanity.com/paper/2111.13463/) (2021)
- [Database Search Results Disambiguation for Task-Oriented Dialog Systems](https://mlsanity.com/paper/2112.08351/) (2021)
- [Towards Asking Clarification Questions for Information Seeking on Task-Oriented Dialogues](https://mlsanity.com/paper/2305.13690/) (2023)
- [Bridging Background Knowledge Gaps in Translation with Automatic Explicitation](https://mlsanity.com/paper/2312.01308/) (2023)
- [Imagining a Future of Designing with AI: Dynamic Grounding, Constructive Negotiation, and Sustainable Motivation](https://mlsanity.com/paper/2402.07342/) (2024)
- [Nutri-bullets: Summarizing Health Studies by Composing Segments](https://mlsanity.com/paper/2103.11921/) (2021)
- [Closed-book Question Generation via Contrastive Learning](https://mlsanity.com/paper/2210.06781/) (2022)
- [CONSISTENT: Open-Ended Question Generation From News Articles](https://mlsanity.com/paper/2210.11536/) (2022)
- [Disambiguation in Conversational Question Answering in the Era of LLMs and Agents: A Survey](https://mlsanity.com/paper/2505.12543/) (2025)
- [Optimizing Question Semantic Space for Dynamic Retrieval-Augmented Multi-hop Question Answering](https://mlsanity.com/paper/2506.00491/) (2025)
- [The Knowledge Alignment Problem: Bridging Human and External Knowledge for Large Language Models](https://mlsanity.com/paper/2305.13669/) (2023)
- [InfoGatherer: Principled Information Seeking via Evidence Retrieval and Strategic Questioning](https://mlsanity.com/paper/2603.05909/) (2026)

## Abstract (arXiv)

We present an approach for generating clarification questions with the goal of eliciting new information that would make the given textual context more complete. We propose that modeling hypothetical answers (to clarification questions) as latent variables can guide our approach into generating more useful clarification questions. We develop a Generative Adversarial Network (GAN) where the generator is a sequence-to-sequence model and the discriminator is a utility function that models the value of updating the context with the answer to the clarification question. We evaluate on two datasets, using both automatic metrics and human judgments of usefulness, specificity and relevance, showing that our approach outperforms both a retrieval-based model and ablations that exclude the utility model and the adversarial training.