Ask or Answer: A Decision Framework for Multi-Turn Health Misinformation Intervention

2026-08-21

AI Summary

研究提出RO-PnR框架，通过在对话中智能选择提问或直接纠正来更有效地干预健康误导信息，减少不必要的互动回合。

Abstract

Correcting health misinformation in dialogue requires more than producing a factual rebuttal: users differ in what they know, what they believe, and what they need to hear, so an effective intervention often depends on first asking the right clarifying question. Yet existing methods either respond immediately or probe indiscriminately, treating clarification as either unnecessary or always beneficial. We propose Reward-Optimized Probe-and-Respond (RO-PnR), a framework that learns when asking is worth its cost. At each turn, RO-PnR chooses between probing for more information and committing to a final correction, guided by a turn-level reward that weighs the expected gain from probing against its interaction cost. To capture how user heterogeneity affects probing value, we model each simulated user with a latent state along health literacy and belief commitment. Experiments show that RO-PnR achieves the highest cost-adjusted utility across three health-misinformation datasets and three base models, using 30% fewer turns than always-probe baselines.

Problem

• health misinformation
• dialogue
• clarifying question
• user heterogeneity
• interaction cost

Innovation

• Reward-Optimized Probe-and-Respond
• turn-level reward
• health literacy
• belief commitment
• cost-adjusted utility