mlsanityData to 14 Oct 2026

Answer-based Adversarial Training for Generating Clarification Questions

arXiv 1904.02281 ↗First posted 4 Apr 2019cs.CLcited by 43

Not on the map. Why?

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.

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

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 10; 2022: 12; 2023: 9; 2024: 6; 2025: 2; 2026: 4.

43 papers.

Sort:

By area:

  1. 2022Measuring and Narrowing the Compositionality Gap in Language Modelscited by 1,075
  2. 2022Distilling Reasoning Capabilities into Smaller Language Modelscited by 158
  3. 2024STaR-GATE: Teaching Language Models to Ask Clarifying Questionscited by 104
  4. 2022CLAM: Selective Clarification for Ambiguous Questions with Generative Language Modelscited by 69
  5. 2022Neural Approaches to Conversational Information Retrievalcited by 42
  6. 2021Ask what's missing and what's useful: Improving Clarification Question Generation using Global Knowledgecited by 40
  7. 2021Controllable Open-ended Question Generation with A New Question Type Ontologycited by 36
  8. 2022ClarifyDelphi: Reinforced Clarification Questions with Defeasibility Rewards for Social and Moral Situationscited by 36
  9. 2022Varifocal Question Generation for Fact-checkingcited by 27
  10. 2022Evaluating Mixed-initiative Conversational Search Systems via User Simulationcited by 25
  11. 2024A Survey of Conversational Searchcited by 22
  12. 2024CLARINET: Augmenting Language Models to Ask Clarification Questions for Retrievalcited by 20
31 more
  1. 2023QUDEVAL: The Evaluation of Questions Under Discussion Discourse Parsingcited by 19
  2. 2021A Review of Text Style Transfer using Deep Learningcited by 18
  3. 2022A Survey on Medical Document Summarizationcited by 14
  4. 2023Zero-shot Clarifying Question Generation for Conversational Searchcited by 14
  5. 2023FOLLOWUPQG: Towards Information-Seeking Follow-up Question Generationcited by 12
  6. 2021Diverse and Specific Clarification Question Generation with Keywordscited by 10
  7. 2021Generating Usage-related Questions for Preference Elicitation in Conversational Recommender Systemscited by 10
  8. 2021Database Search Results Disambiguation for Task-Oriented Dialog Systemscited by 10
  9. 2023Towards Asking Clarification Questions for Information Seeking on Task-Oriented Dialoguescited by 7
  10. 2023Bridging Background Knowledge Gaps in Translation with Automatic Explicitationcited by 7
  11. 2024Imagining a Future of Designing with AI: Dynamic Grounding, Constructive Negotiation, and Sustainable Motivationcited by 7
  12. 2021Nutri-bullets: Summarizing Health Studies by Composing Segmentscited by 6
  13. 2022Closed-book Question Generation via Contrastive Learningcited by 6
  14. 2022CONSISTENT: Open-Ended Question Generation From News Articlescited by 6
  15. 2025Disambiguation in Conversational Question Answering in the Era of LLMs and Agents: A Surveycited by 6
  16. 2025Optimizing Question Semantic Space for Dynamic Retrieval-Augmented Multi-hop Question Answeringcited by 6
  17. 2023The Knowledge Alignment Problem: Bridging Human and External Knowledge for Large Language Modelscited by 3
  18. 2026InfoGatherer: Principled Information Seeking via Evidence Retrieval and Strategic Questioningcited by 3
  19. 2022PReGAN: Answer Oriented Passage Ranking with Weakly Supervised GANcited by 2
  20. 2023Alexpaca: Learning Factual Clarification Question Generation Without Examplescited by 2
  21. 2024Corpus-informed Retrieval Augmented Generation of Clarifying Questionscited by 2
  22. 2024ECIS-VQG: Generation of Entity-centric Information-seeking Questions from Videoscited by 2
  23. 2023SmartProbe: A Virtual Moderator for Market Research Surveyscited by 1
  24. 2021Semantic-Based Self-Critical Training For Question Generationcited by 0
  25. 2021How Well Do You Know Your Audience? Toward Socially-aware Question Generationcited by 0
  26. 2021Multi-stage Clarification in Conversational AI: The case of Question-Answering Dialogue Systemscited by 0
  27. 2022Learning to Diversify for Product Question Generationcited by 0
  28. 2023From text to multimodal: a survey of adversarial example generation in question answering systemscited by 0
  29. 2026Clarification Is Not Enough: Post-Clarification Answering Remains the Bottleneck in Multi-Turn QAcited by 0
  30. 2026Litmus: Zero-Label, Code-Driven Metric Specification for Evaluating AI Systemscited by 0
  31. 2026Learning to Clarify Underspecified Intents Under Limited Interactioncited by 0