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

arXiv: https://arxiv.org/abs/2608.21721 · HTML: https://mlsanity.com/paper/2608.21721/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 30 of its 58 references that are in the map.
- First posted on arXiv 22 Aug 2026.

## Builds on (most cited first, 30 of 30)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [LaMP: When Large Language Models Meet Personalization](https://mlsanity.com/paper/2304.11406/) (2023)
- [LLMs Get Lost In Multi-Turn Conversation](https://mlsanity.com/paper/2505.06120/) (2025)
- [LLMs instead of Human Judges? A Large Scale Empirical Study across 20 NLP Evaluation Tasks](https://mlsanity.com/paper/2406.18403/) (2024)
- [ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL](https://mlsanity.com/paper/2402.19446/) (2024)
- [Explainable Automated Fact-Checking for Public Health Claims](https://mlsanity.com/paper/2010.09926/) (2020)
- [Judging the Judges: Evaluating Alignment and Vulnerabilities in LLMs-as-Judges](https://mlsanity.com/paper/2406.12624/) (2024)
- [MediQ: Question-Asking LLMs and a Benchmark for Reliable Interactive Clinical Reasoning](https://mlsanity.com/paper/2406.00922/) (2024)
- [CollabLLM: From Passive Responders to Active Collaborators](https://mlsanity.com/paper/2502.00640/) (2025)
- [Clarify When Necessary: Resolving Ambiguity Through Interaction with LMs](https://mlsanity.com/paper/2311.09469/) (2023)
- [An Empirical Study of LLM-as-a-Judge for LLM Evaluation: Fine-tuned Judge Model is not a General Substitute for GPT-4](https://mlsanity.com/paper/2403.02839/) (2024)
- [Learning to Clarify: Multi-turn Conversations with Action-Based Contrastive Self-Training](https://mlsanity.com/paper/2406.00222/) (2024)
- [Know You First and Be You Better: Modeling Human-Like User Simulators via Implicit Profiles](https://mlsanity.com/paper/2502.18968/) (2025)
- [Reinforcement Learning-based Counter-Misinformation Response Generation: A Case Study of COVID-19 Vaccine Misinformation](https://mlsanity.com/paper/2303.06433/) (2023)
- [SimUSER: Simulating User Behavior with Large Language Models for Recommender System Evaluation](https://mlsanity.com/paper/2504.12722/) (2025)
- [Evidence-Driven Retrieval Augmented Response Generation for Online Misinformation](https://mlsanity.com/paper/2403.14952/) (2024)
- [Regressing the Relative Future: Efficient Policy Optimization for Multi-turn RLHF](https://mlsanity.com/paper/2410.04612/) (2024)
- [Enhancing Personalized Multi-Turn Dialogue with Curiosity Reward](https://mlsanity.com/paper/2504.03206/) (2025)
- [Ask Patients with Patience: Enabling LLMs for Human-Centric Medical Dialogue with Grounded Reasoning](https://mlsanity.com/paper/2502.07143/) (2025)
- [Contextualized Counterspeech: Strategies for Adaptation, Personalization, and Evaluation](https://mlsanity.com/paper/2412.07338/) (2024)
- [Value of Information: A Framework for Human-Agent Communication](https://mlsanity.com/paper/2601.06407/) (2026)
- [Can You Share Your Story? Modeling Clients' Metacognition and Openness for LLM Therapist Evaluation](https://mlsanity.com/paper/2507.19643/) (2025)
- [MisinfoEval: Generative AI in the Era of "Alternative Facts"](https://mlsanity.com/paper/2410.09949/) (2024)
- [DiverseDialogue: A Methodology for Designing Chatbots with Human-Like Diversity](https://mlsanity.com/paper/2409.00262/) (2024)
- [Rescuing Counterspeech: A Bridging-Based Approach to Combating Misinformation](https://mlsanity.com/paper/2410.12699/) (2024)
- [Speaking at the Right Level: Literacy-Controlled Counterspeech Generation with RAG-RL](https://mlsanity.com/paper/2509.01058/) (2025)
- [Decide less, communicate more: On the construct validity of end-to-end fact-checking in medicine](https://mlsanity.com/paper/2506.20876/) (2025)
- [First Ask Then Answer: A Framework Design for AI Dialogue Based on Supplementary Questioning with Large Language Models](https://mlsanity.com/paper/2508.08308/) (2025)
- [Synthetic Users, Real Differences: an Evaluation Framework for User Simulation in Multi-Turn Conversations](https://mlsanity.com/paper/2605.02624/) (2026)

## Abstract (arXiv)

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.