mlsanityData to 7 Oct 2026

Ask what's missing and what's useful: Improving Clarification Question Generation using Global Knowledge

arXiv 2104.06828 ↗First posted 14 Apr 2021cs.CLcited by 40

Not on the map. Why?

Abstract (arXiv)

The ability to generate clarification questions i.e., questions that identify useful missing information in a given context, is important in reducing ambiguity. Humans use previous experience with similar contexts to form a global view and compare it to the given context to ascertain what is missing and what is useful in the context. Inspired by this, we propose a model for clarification question generation where we first identify what is missing by taking a difference between the global and the local view and then train a model to identify what is useful and generate a question about it. Our model outperforms several baselines as judged by both automatic metrics and humans.

Key facts. Cited by 40 papers in the map (data through 7 Oct 2026). Builds on 26 of its 44 references that are in the map. First posted on arXiv 14 Apr 2021.

Builds on

26 of 44 references.

References · 26

  1. 2017Attention Is All You Needcited by 59,932
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  3. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  4. 2015A Diversity-Promoting Objective Function for Neural Conversation Modelscited by 1,068
  5. 2019Plug and Play Language Models: A Simple Approach to Controlled Text Generationcited by 793
  6. 2019CTRL: A Conditional Transformer Language Model for Controllable Generationcited by 754
  7. 2020Stanza: A Python Natural Language Processing Toolkit for Many Human Languagescited by 719
  8. 2015Image-based Recommendations on Styles and Substitutescited by 702
  9. 2018QuAC : Question Answering in Contextcited by 379
  10. 2018Plan-And-Write: Towards Better Automatic Storytellingcited by 232
  11. 2015The Ubuntu Dialogue Corpus: A Large Dataset for Research in Unstructured Multi-Turn Dialogue Systemscited by 172
  12. 2019What makes a good conversation? How controllable attributes affect human judgmentscited by 140
14 more
  1. 2019Asking Clarifying Questions in Open-Domain Information-Seeking Conversationscited by 136
  2. 2018Learning to Write with Cooperative Discriminatorscited by 119
  3. 2018Learning to Ask Good Questions: Ranking Clarification Questions using Neural Expected Value of Perfect Informationcited by 110
  4. 2019Addressing Semantic Drift in Question Generation for Semi-Supervised Question Answeringcited by 63
  5. 2019What Makes a Good Conversation? Challenges in Designing Truly Conversational Agentscited by 42
  6. 2019Answer-based Adversarial Training for Generating Clarification Questionscited by 42
  7. 2019Using Local Knowledge Graph Construction to Scale Seq2Seq Models to Multi-Document Inputscited by 38
  8. 2020ClarQ: A large-scale and diverse dataset for Clarification Question Generationcited by 31
  9. 2015Addressing Complex and Subjective Product-Related Queries with Customer Reviewscited by 28
  10. 2020Stay Hungry, Stay Focused: Generating Informative and Specific Questions in Information-Seeking Conversationscited by 19
  11. 2018Building Dynamic Knowledge Graphs from Text using Machine Reading Comprehensioncited by 17
  12. 2019Towards Open Intent Discovery for Conversational Textcited by 13
  13. 2017Neural Models for Key Phrase Detection and Question Generationcited by 9
  14. 2016Getting More Out Of Syntax with PropScited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 10; 2023: 8; 2024: 10; 2025: 5; 2026: 6.

40 papers.

Sort:

By area:

  1. 2022Pretrained Language Models for Text Generation: A Surveycited by 121
  2. 2024The Art of Saying No: Contextual Noncompliance in Language Modelscited by 100
  3. 2022Generating Literal and Implied Subquestions to Fact-check Complex Claimscited by 66
  4. 2024Synthetic Dialogue Dataset Generation using LLM Agentscited by 39
  5. 2022ClarifyDelphi: Reinforced Clarification Questions with Defeasibility Rewards for Social and Moral Situationscited by 36
  6. 2024Data-driven Discovery with Large Generative Modelscited by 33
  7. 2022Varifocal Question Generation for Fact-checkingcited by 27
  8. 2021Detect and Perturb: Neutral Rewriting of Biased and Sensitive Text via Gradient-based Decodingcited by 23
  9. 2024On Overcoming Miscalibrated Conversational Priors in LLM-based Chatbotscited by 23
  10. 2024A Survey of Conversational Searchcited by 22
  11. 2022Python Code Generation by Asking Clarification Questionscited by 16
  12. 2026HiL-Bench (Human-in-Loop Benchmark): Do Agents Know When to Ask for Help?cited by 16
28 more
  1. 2023Rephrase, Augment, Reason: Visual Grounding of Questions for Vision-Language Modelscited by 14
  2. 2024InfoLossQA: Characterizing and Recovering Information Loss in Text Simplificationcited by 14
  3. 2023FOLLOWUPQG: Towards Information-Seeking Follow-up Question Generationcited by 12
  4. 2024Contextualized Evaluations: Judging Language Model Responses to Underspecified Queriescited by 12
  5. 2022Emp-RFT: Empathetic Response Generation via Recognizing Feature Transitions between Utterancescited by 11
  6. 2023Instruction Clarification Requests in Multimodal Collaborative Dialogue Games: Tasks, and an Analysis of the CoDraw Datasetcited by 11
  7. 2023Product Question Answering in E-Commerce: A Surveycited by 10
  8. 2023Towards Asking Clarification Questions for Information Seeking on Task-Oriented Dialoguescited by 7
  9. 2022CONSISTENT: Open-Ended Question Generation From News Articlescited by 6
  10. 2024I Could've Asked That: Reformulating Unanswerable Questionscited by 6
  11. 2025Referential ambiguity and clarification requests: comparing human and LLM behaviourcited by 5
  12. 2024Estimating the Usefulness of Clarifying Questions and Answers for Conversational Searchcited by 4
  13. 2024Taking Action Towards Graceful Interaction: The Effects of Performing Actions on Modelling Policies for Instruction Clarification Requestscited by 4
  14. 2022Achieving Conversational Goals with Unsupervised Post-hoc Knowledge Injectioncited by 3
  15. 2023The Knowledge Alignment Problem: Bridging Human and External Knowledge for Large Language Modelscited by 3
  16. 2026InfoGatherer: Principled Information Seeking via Evidence Retrieval and Strategic Questioningcited by 3
  17. 2022A Transformer-Based User Satisfaction Prediction for Proactive Interaction Mechanism in DuerOScited by 2
  18. 2025Bridging Information Gaps with Comprehensive Answers: Improving the Diversity and Informativeness of Follow-Up Questionscited by 2
  19. 2023Discourse over Discourse: The Need for an Expanded Pragmatic Focus in Conversational AIcited by 1
  20. 2025Exploring the Secondary Risks of Large Language Modelscited by 1
  21. 2025How2: How to learn from procedural How-to questionscited by 1
  22. 2026Act or Clarify? Modeling Sensitivity to Uncertainty and Cost in Communicationcited by 1
  23. 2022Learning to Diversify for Product Question Generationcited by 0
  24. 2023Expanding the Set of Pragmatic Considerations in Conversational AIcited by 0
  25. 2025Reward-Driven Interaction: Enhancing Proactive Dialogue Agents through User Satisfaction Predictioncited by 0
  26. 2026DiscoTrace: Representing and Comparing Answering Strategies of Humans and LLMs in Information-Seeking Question Answeringcited by 0
  27. 2026Litmus: Zero-Label, Code-Driven Metric Specification for Evaluating AI Systemscited by 0
  28. 2026TRACE: Trustworthy Retrieval-Augmented Conversational Enginecited by 0