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

TL;DR

This paper investigates how dialogue systems can better generate clarification questions by aligning model uncertainty with human behavior, proposing a new approach that improves task success.

Contribution

It introduces a novel method for generating clarification questions based on model uncertainty, addressing the gap between model and human uncertainty behaviors.

Findings

Model uncertainty does not naturally mirror human clarification behavior.

Using model uncertainty for question generation improves task success.

The proposed approach outperforms several baselines in clarification effectiveness.

Abstract

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.