# Asking the Right Question at the Right Time: Human and Model Uncertainty Guidance to Ask Clarification Questions

arXiv: https://arxiv.org/abs/2402.06509 · HTML: https://mlsanity.com/paper/2402.06509/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 74 references that are in the map.
- First posted on arXiv 9 Feb 2024.

## Builds on (most cited first, 28 of 28)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?](https://mlsanity.com/paper/1703.04977/) (2017)
- [Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift](https://mlsanity.com/paper/1906.02530/) (2019)
- [Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methods](https://mlsanity.com/paper/1910.09457/) (2019)
- [TEACh: Task-driven Embodied Agents that Chat](https://mlsanity.com/paper/2110.00534/) (2021)
- [Prompting and Evaluating Large Language Models for Proactive Dialogues: Clarification, Target-guided, and Non-collaboration](https://mlsanity.com/paper/2305.13626/) (2023)
- [Help, Anna! Visual Navigation with Natural Multimodal Assistance via Retrospective Curiosity-Encouraging Imitation Learning](https://mlsanity.com/paper/1909.01871/) (2019)
- [Building and Evaluating Open-Domain Dialogue Corpora with Clarifying Questions](https://mlsanity.com/paper/2109.05794/) (2021)
- [Uncertainty in Natural Language Generation: From Theory to Applications](https://mlsanity.com/paper/2307.15703/) (2023)
- [Just Ask:An Interactive Learning Framework for Vision and Language Navigation](https://mlsanity.com/paper/1912.00915/) (2019)
- [Grounding 'Grounding' in NLP](https://mlsanity.com/paper/2106.02192/) (2021)
- [A Comparison of LSTM and BERT for Small Corpus](https://mlsanity.com/paper/2009.05451/) (2020)
- [Learning to Execute Actions or Ask Clarification Questions](https://mlsanity.com/paper/2204.08373/) (2022)
- [IGLU 2022: Interactive Grounded Language Understanding in a Collaborative Environment at NeurIPS 2022](https://mlsanity.com/paper/2205.13771/) (2022)
- [Hierarchical Conditional Relation Networks for Multimodal Video Question Answering](https://mlsanity.com/paper/2010.10019/) (2020)
- [A recipe for annotating grounded clarifications](https://mlsanity.com/paper/2104.08964/) (2021)
- [Dialog Acts for Task-Driven Embodied Agents](https://mlsanity.com/paper/2209.12953/) (2022)
- [Conversation as Action Under Uncertainty](https://mlsanity.com/paper/1301.3883/) (2013)
- [How Should Agents Ask Questions For Situated Learning? An Annotated Dialogue Corpus](https://mlsanity.com/paper/2106.06504/) (2021)
- [Instruction Clarification Requests in Multimodal Collaborative Dialogue Games: Tasks, and an Analysis of the CoDraw Dataset](https://mlsanity.com/paper/2302.14406/) (2023)
- [Diverse and Specific Clarification Question Generation with Keywords](https://mlsanity.com/paper/2104.10317/) (2021)
- [Collecting Interactive Multi-modal Datasets for Grounded Language Understanding](https://mlsanity.com/paper/2211.06552/) (2022)
- [Looking for Confirmations: An Effective and Human-Like Visual Dialogue Strategy](https://mlsanity.com/paper/2109.05312/) (2021)
- [ELBA: Learning by Asking for Embodied Visual Navigation and Task Completion](https://mlsanity.com/paper/2302.04865/) (2023)

## Built on by (most cited first, 30 of 32)

- [Ambig-SWE: Interactive Agents to Overcome Underspecificity in Software Engineering](https://mlsanity.com/paper/2502.13069/) (2025)
- [A Survey of Conversational Search](https://mlsanity.com/paper/2410.15576/) (2024)
- [Ask or Assume? Uncertainty-Aware Clarification-Seeking in Coding Agents](https://mlsanity.com/paper/2603.26233/) (2026)
- [Talk Less, Interact Better: Evaluating In-context Conversational Adaptation in Multimodal LLMs](https://mlsanity.com/paper/2408.01417/) (2024)
- [Anthropomimetic Uncertainty: What Verbalized Uncertainty in Language Models is Missing](https://mlsanity.com/paper/2507.10587/) (2025)
- [The Road to Artificial SuperIntelligence: A Comprehensive Survey of Superalignment](https://mlsanity.com/paper/2412.16468/) (2024)
- [Contextualized Evaluations: Judging Language Model Responses to Underspecified Queries](https://mlsanity.com/paper/2411.07237/) (2024)
- [AmbiK: Dataset of Ambiguous Tasks in Kitchen Environment](https://mlsanity.com/paper/2506.04089/) (2025)
- [RAcQUEt: Unveiling the Dangers of Overlooked Referential Ambiguity in Visual LLMs](https://mlsanity.com/paper/2412.13835/) (2024)
- [Do Pre-Trained Language Models Detect and Understand Semantic Underspecification? Ask the DUST!](https://mlsanity.com/paper/2402.12486/) (2024)
- [Clarify Before You Draw: Proactive Agents for Robust Text-to-CAD Generation](https://mlsanity.com/paper/2602.03045/) (2026)
- [Referential ambiguity and clarification requests: comparing human and LLM behaviour](https://mlsanity.com/paper/2507.10445/) (2025)
- [Broadening Access to Simulations for End-Users via Large Language Models: Challenges and Opportunities](https://mlsanity.com/paper/2409.15290/) (2024)
- [Characterizing Language Use in a Collaborative Situated Game](https://mlsanity.com/paper/2512.03381/) (2025)
- [Same Evidence, Different Answers: Canonical-Context On-Policy Distillation for Multi-Turn Language Models](https://mlsanity.com/paper/2605.30251/) (2026)
- [Reference Games as a Testbed for the Alignment of Model Uncertainty and Clarification Requests](https://mlsanity.com/paper/2601.07820/) (2026)
- [Task-Aware Delegation Cues for LLM Agents](https://mlsanity.com/paper/2603.11011/) (2026)
- [Remember, Verify, or Ask? Cross-Family Evaluation of Memory Commitment in LLM Agents](https://mlsanity.com/paper/2608.19564/) (2026)
- [Proactive Service Agents: A Unified Decision Framework, Methods, and Evaluation](https://mlsanity.com/paper/2609.03727/) (2026)
- [It Couldn't Help But Overhear: On the Limits of Modelling Meta-Communicative Grounding Acts with Supervised Learning](https://mlsanity.com/paper/2405.01139/) (2024)
- [Research Superalignment Should Advance Now with Alternating Competence and Conformity Optimization](https://mlsanity.com/paper/2503.07660/) (2025)
- [How2: How to learn from procedural How-to questions](https://mlsanity.com/paper/2510.11144/) (2025)
- [NRR-Core: Non-Resolution Reasoning as a Computational Framework for Contextual Identity and Ambiguity Preservation](https://mlsanity.com/paper/2512.13478/) (2025)
- [Act or Clarify? Modeling Sensitivity to Uncertainty and Cost in Communication](https://mlsanity.com/paper/2602.02843/) (2026)
- [Clarify, Abstain or Answer? Strategising in Conversation with Belief-Augmented Generation](https://mlsanity.com/paper/2605.25831/) (2026)
- [NRR-Phi: A Typed External Text-to-State Interface and Update Contract for Inspectable Ambiguity-State Maintenance](https://mlsanity.com/paper/2601.19933/) (2026)
- [When Contextual Inference Fails: Cancelability in Interactive Instruction Following](https://mlsanity.com/paper/2603.19997/) (2026)
- [The Image Reconstruction Game: Drawing Common Ground Through Iterative Multimodal Dialogue](https://mlsanity.com/paper/2606.01901/) (2026)
- [Beyond Local Surprise: Grounded Dialogue as Selective Belief Revision under Referential Uncertainty](https://mlsanity.com/paper/2608.26035/) (2026)
- [HerHealthEval: Evaluating Multilingual and Register-Sensitive Understanding of Women's Health Communication](https://mlsanity.com/paper/2609.20684/) (2026)

## Abstract (arXiv)

Clarification questions are an essential dialogue tool to signal misunderstanding, ambiguities, and under-specification in language use. While humans are able to resolve uncertainty by asking questions since childhood, modern dialogue systems struggle to generate effective questions. To make progress in this direction, in this work we take a collaborative dialogue task as a testbed and study how model uncertainty relates to human uncertainty -- an as yet under-explored problem. We show that model uncertainty does not mirror human clarification-seeking behavior, which suggests that using human clarification questions as supervision for deciding when to ask may not be the most effective way to resolve model uncertainty. To address this issue, we propose an approach to generating clarification questions based on model uncertainty estimation, compare it to several alternatives, and show that it leads to significant improvements in terms of task success. Our findings highlight the importance of equipping dialogue systems with the ability to assess their own uncertainty and exploit in interaction.