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

arXiv: https://arxiv.org/abs/2104.06828 · HTML: https://mlsanity.com/paper/2104.06828/

## Key facts

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

## Builds on (most cited first, 26 of 26)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [A Diversity-Promoting Objective Function for Neural Conversation Models](https://mlsanity.com/paper/1510.03055/) (2015)
- [Plug and Play Language Models: A Simple Approach to Controlled Text Generation](https://mlsanity.com/paper/1912.02164/) (2019)
- [CTRL: A Conditional Transformer Language Model for Controllable Generation](https://mlsanity.com/paper/1909.05858/) (2019)
- [Stanza: A Python Natural Language Processing Toolkit for Many Human Languages](https://mlsanity.com/paper/2003.07082/) (2020)
- [Image-based Recommendations on Styles and Substitutes](https://mlsanity.com/paper/1506.04757/) (2015)
- [QuAC : Question Answering in Context](https://mlsanity.com/paper/1808.07036/) (2018)
- [Plan-And-Write: Towards Better Automatic Storytelling](https://mlsanity.com/paper/1811.05701/) (2018)
- [The Ubuntu Dialogue Corpus: A Large Dataset for Research in Unstructured Multi-Turn Dialogue Systems](https://mlsanity.com/paper/1506.08909/) (2015)
- [What makes a good conversation? How controllable attributes affect human judgments](https://mlsanity.com/paper/1902.08654/) (2019)
- [Asking Clarifying Questions in Open-Domain Information-Seeking Conversations](https://mlsanity.com/paper/1907.06554/) (2019)
- [Learning to Write with Cooperative Discriminators](https://mlsanity.com/paper/1805.06087/) (2018)
- [Learning to Ask Good Questions: Ranking Clarification Questions using Neural Expected Value of Perfect Information](https://mlsanity.com/paper/1805.04655/) (2018)
- [Addressing Semantic Drift in Question Generation for Semi-Supervised Question Answering](https://mlsanity.com/paper/1909.06356/) (2019)
- [Answer-based Adversarial Training for Generating Clarification Questions](https://mlsanity.com/paper/1904.02281/) (2019)
- [What Makes a Good Conversation? Challenges in Designing Truly Conversational Agents](https://mlsanity.com/paper/1901.06525/) (2019)
- [Using Local Knowledge Graph Construction to Scale Seq2Seq Models to Multi-Document Inputs](https://mlsanity.com/paper/1910.08435/) (2019)
- [ClarQ: A large-scale and diverse dataset for Clarification Question Generation](https://mlsanity.com/paper/2006.05986/) (2020)
- [Addressing Complex and Subjective Product-Related Queries with Customer Reviews](https://mlsanity.com/paper/1512.06863/) (2015)
- [Stay Hungry, Stay Focused: Generating Informative and Specific Questions in Information-Seeking Conversations](https://mlsanity.com/paper/2004.14530/) (2020)
- [Building Dynamic Knowledge Graphs from Text using Machine Reading Comprehension](https://mlsanity.com/paper/1810.05682/) (2018)
- [Towards Open Intent Discovery for Conversational Text](https://mlsanity.com/paper/1904.08524/) (2019)
- [Neural Models for Key Phrase Detection and Question Generation](https://mlsanity.com/paper/1706.04560/) (2017)
- [Getting More Out Of Syntax with PropS](https://mlsanity.com/paper/1603.01648/) (2016)

## Built on by (most cited first, 30 of 40)

- [Pretrained Language Models for Text Generation: A Survey](https://mlsanity.com/paper/2201.05273/) (2022)
- [The Art of Saying No: Contextual Noncompliance in Language Models](https://mlsanity.com/paper/2407.12043/) (2024)
- [Generating Literal and Implied Subquestions to Fact-check Complex Claims](https://mlsanity.com/paper/2205.06938/) (2022)
- [Synthetic Dialogue Dataset Generation using LLM Agents](https://mlsanity.com/paper/2401.17461/) (2024)
- [ClarifyDelphi: Reinforced Clarification Questions with Defeasibility Rewards for Social and Moral Situations](https://mlsanity.com/paper/2212.10409/) (2022)
- [Data-driven Discovery with Large Generative Models](https://mlsanity.com/paper/2402.13610/) (2024)
- [Varifocal Question Generation for Fact-checking](https://mlsanity.com/paper/2210.12400/) (2022)
- [HiL-Bench (Human-in-Loop Benchmark): Do Agents Know When to Ask for Help?](https://mlsanity.com/paper/2604.09408/) (2026)
- [On Overcoming Miscalibrated Conversational Priors in LLM-based Chatbots](https://mlsanity.com/paper/2406.01633/) (2024)
- [Detect and Perturb: Neutral Rewriting of Biased and Sensitive Text via Gradient-based Decoding](https://mlsanity.com/paper/2109.11708/) (2021)
- [A Survey of Conversational Search](https://mlsanity.com/paper/2410.15576/) (2024)
- [Python Code Generation by Asking Clarification Questions](https://mlsanity.com/paper/2212.09885/) (2022)
- [Rephrase, Augment, Reason: Visual Grounding of Questions for Vision-Language Models](https://mlsanity.com/paper/2310.05861/) (2023)
- [InfoLossQA: Characterizing and Recovering Information Loss in Text Simplification](https://mlsanity.com/paper/2401.16475/) (2024)
- [FOLLOWUPQG: Towards Information-Seeking Follow-up Question Generation](https://mlsanity.com/paper/2309.05007/) (2023)
- [Contextualized Evaluations: Judging Language Model Responses to Underspecified Queries](https://mlsanity.com/paper/2411.07237/) (2024)
- [Emp-RFT: Empathetic Response Generation via Recognizing Feature Transitions between Utterances](https://mlsanity.com/paper/2205.03112/) (2022)
- [Instruction Clarification Requests in Multimodal Collaborative Dialogue Games: Tasks, and an Analysis of the CoDraw Dataset](https://mlsanity.com/paper/2302.14406/) (2023)
- [Product Question Answering in E-Commerce: A Survey](https://mlsanity.com/paper/2302.08092/) (2023)
- [Towards Asking Clarification Questions for Information Seeking on Task-Oriented Dialogues](https://mlsanity.com/paper/2305.13690/) (2023)
- [CONSISTENT: Open-Ended Question Generation From News Articles](https://mlsanity.com/paper/2210.11536/) (2022)
- [I Could've Asked That: Reformulating Unanswerable Questions](https://mlsanity.com/paper/2407.17469/) (2024)
- [Referential ambiguity and clarification requests: comparing human and LLM behaviour](https://mlsanity.com/paper/2507.10445/) (2025)
- [Estimating the Usefulness of Clarifying Questions and Answers for Conversational Search](https://mlsanity.com/paper/2401.11463/) (2024)
- [Taking Action Towards Graceful Interaction: The Effects of Performing Actions on Modelling Policies for Instruction Clarification Requests](https://mlsanity.com/paper/2401.17039/) (2024)
- [Achieving Conversational Goals with Unsupervised Post-hoc Knowledge Injection](https://mlsanity.com/paper/2203.11399/) (2022)
- [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)
- [A Transformer-Based User Satisfaction Prediction for Proactive Interaction Mechanism in DuerOS](https://mlsanity.com/paper/2212.03817/) (2022)
- [Bridging Information Gaps with Comprehensive Answers: Improving the Diversity and Informativeness of Follow-Up Questions](https://mlsanity.com/paper/2502.17715/) (2025)

## 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.