Act or Clarify? Modeling Sensitivity to Uncertainty and Cost in Communication

• URL: http://arxiv.org/abs/2602.02843v2
• Date: Wed, 04 Feb 2026 07:50:43 GMT
• Title: Act or Clarify? Modeling Sensitivity to Uncertainty and Cost in Communication
• Authors: Polina Tsvilodub, Karl Mulligan, Todd Snider, Robert D. Hawkins, Michael Franke,
• Abstract summary: In communicative settings, an important way of reducing uncertainty is by asking clarification questions (CQs)<n>We predict that the decision to ask a CQ depends on both contextual uncertainty and the cost of alternative actions.<n>We formalize this interaction in a computational model based on expected regret.
• Score: 4.986551765990419
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: When deciding how to act under uncertainty, agents may choose to act to reduce uncertainty or they may act despite that uncertainty. In communicative settings, an important way of reducing uncertainty is by asking clarification questions (CQs). We predict that the decision to ask a CQ depends on both contextual uncertainty and the cost of alternative actions, and that these factors interact: uncertainty should matter most when acting incorrectly is costly. We formalize this interaction in a computational model based on expected regret: how much an agent stands to lose by acting now rather than with full information. We test these predictions in two experiments, one examining purely linguistic responses to questions and another extending to choices between clarification and non-linguistic action. Taken together, our results suggest a rational tradeoff: humans tend to seek clarification proportional to the risk of substantial loss when acting under uncertainty.

Related papers

• Do not Abstain! Identify and Solve the Uncertainty [25.744791822890036]
  We introduce bftextConfuseBench, a benchmark mainly focus on three types of uncertainty: document scarcity, limited capability, and query ambiguity.<n>Experiments reveal that current LLMs struggle to accurately identify the root cause of uncertainty and solve it.<n>We first generate context-aware inquiries that highlight the confusing aspect of the original query.<n>Then we judge the source of uncertainty based on the uniqueness of the inquiry's answer.
  arXiv  Detail & Related papers  (2025-06-01T02:15:17Z)
• Position: Uncertainty Quantification Needs Reassessment for Large-language Model Agents [19.974114160377045]
  This position paper argues that this traditional dichotomy of uncertainties is too limited for the open and interactive setup that LLM agents operate in.<n>We propose three novel research directions that focus on uncertainties in such human-computer interactions.
  arXiv  Detail & Related papers  (2025-05-28T17:59:08Z)
• Calibrating Verbal Uncertainty as a Linear Feature to Reduce Hallucinations [51.92795774118647]
  We find that verbal uncertainty'' is governed by a single linear feature in the representation space of LLMs.<n>We show that this has only moderate correlation with the actual semantic uncertainty'' of the model.
  arXiv  Detail & Related papers  (2025-03-18T17:51:04Z)
• Does Knowledge About Perceptual Uncertainty Help an Agent in Automated Driving? [9.729293160819038]
  We investigate how an agent's behavior is influenced by an uncertain perception.<n>We introduce uncertainty in the observation space by perturbing the perception of the given agent.<n>Our experiments show that an unreliable observation space modeled by a perturbed perception leads to a defensive driving behavior of the agent.
  arXiv  Detail & Related papers  (2025-02-17T14:56:25Z)
• Probabilistic Modeling of Disparity Uncertainty for Robust and Efficient Stereo Matching [61.73532883992135]
  We propose a new uncertainty-aware stereo matching framework.<n>We adopt Bayes risk as the measurement of uncertainty and use it to separately estimate data and model uncertainty.
  arXiv  Detail & Related papers  (2024-12-24T23:28:20Z)
• Criticality and Safety Margins for Reinforcement Learning [53.10194953873209]
  We seek to define a criticality framework with both a quantifiable ground truth and a clear significance to users.<n>We introduce true criticality as the expected drop in reward when an agent deviates from its policy for n consecutive random actions.<n>We also introduce the concept of proxy criticality, a low-overhead metric that has a statistically monotonic relationship to true criticality.
  arXiv  Detail & Related papers  (2024-09-26T21:00:45Z)
• Evaluating Theory of (an uncertain) Mind: Predicting the Uncertain Beliefs of Others in Conversation Forecasting [29.892041865029803]
  We propose a new suite of tasks, challenging language models (LMs) to model the uncertainty of others in dialogue. Uniquely, we view interlocutors themselves as forecasters, asking an LM to predict the uncertainty of the interlocutors. While LMs can explain up to 7% variance in the uncertainty of others, we highlight the difficulty of the tasks and room for future work.
  arXiv  Detail & Related papers  (2024-09-23T13:05:25Z)
• Certainly Uncertain: A Benchmark and Metric for Multimodal Epistemic and Aleatoric Awareness [106.52630978891054]
  We present a taxonomy of uncertainty specific to vision-language AI systems. We also introduce a new metric confidence-weighted accuracy, that is well correlated with both accuracy and calibration error.
  arXiv  Detail & Related papers  (2024-07-02T04:23:54Z)
• Uncertainty-Based Abstention in LLMs Improves Safety and Reduces Hallucinations [63.330182403615886]
  A major barrier towards the practical deployment of large language models (LLMs) is their lack of reliability. Three situations where this is particularly apparent are correctness, hallucinations when given unanswerable questions, and safety. In all three cases, models should ideally abstain from responding, much like humans, whose ability to understand uncertainty makes us refrain from answering questions we don't know.
  arXiv  Detail & Related papers  (2024-04-16T23:56:38Z)
• Asking the Right Question at the Right Time: Human and Model Uncertainty Guidance to Ask Clarification Questions [2.3838507844983248]
  We show that model uncertainty does not mirror human clarification-seeking behavior. We propose an approach to generating clarification questions based on model uncertainty estimation.
  arXiv  Detail & Related papers  (2024-02-09T16:15:30Z)
• Clarify When Necessary: Resolving Ambiguity Through Interaction with LMs [58.620269228776294]
  We propose a task-agnostic framework for resolving ambiguity by asking users clarifying questions. We evaluate systems across three NLP applications: question answering, machine translation and natural language inference. We find that intent-sim is robust, demonstrating improvements across a wide range of NLP tasks and LMs.
  arXiv  Detail & Related papers  (2023-11-16T00:18:50Z)
• Improving the Reliability of Large Language Models by Leveraging Uncertainty-Aware In-Context Learning [76.98542249776257]
  Large-scale language models often face the challenge of "hallucination" We introduce an uncertainty-aware in-context learning framework to empower the model to enhance or reject its output in response to uncertainty.
  arXiv  Detail & Related papers  (2023-10-07T12:06:53Z)
• When Does Uncertainty Matter?: Understanding the Impact of Predictive Uncertainty in ML Assisted Decision Making [68.19284302320146]
  We carry out user studies to assess how people with differing levels of expertise respond to different types of predictive uncertainty. We found that showing posterior predictive distributions led to smaller disagreements with the ML model's predictions. This suggests that posterior predictive distributions can potentially serve as useful decision aids which should be used with caution and take into account the type of distribution and the expertise of the human.
  arXiv  Detail & Related papers  (2020-11-12T02:23:53Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.