Why This and Not That? A Collaborative Reflection Approach for Understanding Thought Coverage in Decision Making Support Dialog

2026-08-17

AI Summary

研究通过引入一种以人为中心的方法，让用户解释对话模式背后的原因，以改进决策支持对话中对用户思考覆盖的理解，挑战了仅依赖可观察行为的自适应对话策略。

Abstract

Conversational agents that support reflection for decision making often rely on adaptive dialogue policies that map observed user behavior to actions such as probing, deepening, or redirecting. Yet the same pattern can reflect a range of different reasons such as deliberate prioritisation or limited self-access. By modeling the observable pattern rather than the user's reason for it, current policies risk premature assumptions about the user state and inappropriate next actions. To address this gap, we introduce a human-centered method for surfacing this hidden inference step. In a user study with 62 users and 232 collaborative moments, we pause a reflection-support agent when it would normally redirect the conversation, surface its observation, and ask users to interpret the pattern and decide how to proceed. We derive a taxonomy of nine interpretation categories and show that similar reflective states can call for substantially different follow-up actions. Our findings challenge the assumption that adaptive dialog policies can rely on observable behavior alone, and show how user-provided interpretations can inform more appropriate conversational actions.

Problem

• adaptive dialogue policies
• user behavior
• reflection support
• decision making
• conversational agents

Innovation

• human-centered method
• hidden inference step
• user-provided interpretations
• adaptive dialog policies