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

TL;DR

This paper models how agents decide to ask clarification questions based on uncertainty and action costs, showing humans tend to seek clarification when potential losses are high under uncertainty.

Contribution

It introduces a computational model predicting when agents ask clarification questions, integrating uncertainty and cost factors, and validates it through two experiments.

Findings

Humans ask clarification questions more when the risk of incorrect action is high.

The model accurately predicts human behavior in linguistic and non-linguistic contexts.

Clarification seeking is proportional to potential loss under uncertainty.

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.