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

Xiaoying Song; Anirban Saha Anik; Jinyu Liu; Qitao Tan; Geng Yuan; Lingzi Hong

cs.AIAug 22, 2026

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

Authors: Xiaoying Song, Anirban Saha Anik, Jinyu Liu, Qitao Tan, Geng Yuan, Lingzi Hong

Organizations: University of North Texas · University of Georgia

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.

Figures & tables

Figure 1: Different strategies on the same misinformation post. RO-PnR weighs benefit vs. cost before acting.

Figure 2: Overview of the RO-PnR framework. Top (training): the policy generates candidate actions conditioned on the query and hidden user state; a frozen reference and reward model score the dialogue, and the reward compares Respond (current quality) against Probe (expected future quality minus cost). Group-normalized advantages then update the policy via GRPO. Bottom (inference): the policy interacts with the user over multiple turns, deciding at each step whether to probe or produce a final adaptive response.

Dataset	Method	Llama-3.1-8B-Instruct							Qwen3-8B							Gemma-4-E4B-it
Dataset	Method	AA	PG	TA	Quality	FER $\downarrow$	Turns $\downarrow$	Utility	AA	PG	TA	Quality	FER $\downarrow$	Turns $\downarrow$	Utility	AA	PG	TA	Quality	FER $\downarrow$	Turns $\downarrow$	Utility
CounterHealth	Single-Turn	0.58	0.53	0.61	0.57	0.18	5.00	0.56	0.58	0.52	0.61	0.57	0.15	5.00	0.56	0.64	0.59	0.67	0.63	0.04	5.00	0.62
	Fixed-Q	0.72	0.65	0.76	0.71	0.11	5.00	0.70	0.71	0.64	0.73	0.69	0.08	5.00	0.68	0.73	0.66	0.74	0.71	0.02	5.00	0.70
	Reactive	0.72	0.64	0.76	0.70	0.11	5.00	0.69	0.71	0.64	0.72	0.69	0.09	5.00	0.68	0.72	0.65	0.74	0.71	0.02	3.92	0.70
	Confidence	0.71	0.64	0.74	0.69	0.13	1.26	0.69	0.67	0.61	0.70	0.66	0.06	1.42	0.66	0.72	0.64	0.76	0.71	0.02	1.85	0.71
	SFT	0.70	0.64	0.76	0.70	0.07	4.38	0.69	0.70	0.64	0.76	0.70	0.05	4.22	0.69	0.70	0.64	0.76	0.70	0.09	4.61	0.69

Table 1: Average results across all health-literacy and belief-commitment configurations, for each method, dataset, and base model. AA , PG , TA are the Audience Alignment (AA), Personalized Grounding(PG), and Tailored Actionability (TA) scores (normalized to

[0,1]

); Quality is the overall quality of AA, PG and TA (normalized to

[0,1]

); FER is the factual error rate (

\downarrow

); Turns is the average number of dialogue turns (

\downarrow

); and Utility is the cost-adjusted Quality at

c{=}0.01

, our headline metric (normalized to

[0,1]

		CounterHealth				Misinfo				Pubhealth
Method	Model	F	I	C	Ov.	F	I	C	Q.	F	I	C	Ov.
Single-Turn	Llama	0.51	0.60	0.57	0.56	0.49	0.57	0.55	0.53	0.57	0.64	0.62	0.61
	Qwen	0.50	0.59	0.59	0.56	0.48	0.56	0.56	0.54	0.54	0.63	0.62	0.60
	Gemma	0.54	0.66	0.67	0.62	0.56	0.67	0.67	0.63	0.56	0.67	0.68	0.64
Fixed-Q	Llama	0.66	0.72	0.72	0.70	0.62	0.71	0.70	0.68	0.67	0.73	0.73	0.71
	Qwen	0.62	0.71	0.72	0.68	0.63	0.71	0.70	0.68	0.67	0.72	0.73	0.71

Table 2: Utility by Health Literacy Level (normalized to

[0,1]

). Higher-value cells are highlighted with light tints: green (

\geq 0.70

), mint (

\geq 0.73

), and blue (

\geq 0.75

). F, I, C, Ov., denotes Functional, Interactive, Critical, and all populations.

		CounterHealth				Misinfo				Pubhealth
Method	Model	S	H	O	Ov.	S	H	O	Ov.	S	H	O	Ov.
Single-Turn	Llama	0.50	0.54	0.64	0.56	0.48	0.52	0.61	0.53	0.55	0.57	0.71	0.61
	Qwen	0.50	0.54	0.64	0.56	0.48	0.52	0.60	0.54	0.53	0.57	0.69	0.60
	Gemma	0.57	0.62	0.69	0.62	0.58	0.62	0.69	0.63	0.58	0.62	0.71	0.64
Fixed-Q	Llama	0.63	0.71	0.75	0.70	0.60	0.69	0.74	0.68	0.65	0.72	0.76	0.71
	Qwen	0.61	0.71	0.73	0.68	0.60	0.70	0.73	0.68	0.65	0.72	0.75	0.71

Table 3: Utility by Belief Commitment. Higher-value cells are highlighted with light tints: green (

\geq 0.70

), mint (

\geq 0.73

), and blue (

\geq 0.75

); lower values are left uncolored. S, H, O, Ov., denotes Strong, Hesitant, Open, and all populations.

Variant	AA $\uparrow$	PG $\uparrow$	TA $\uparrow$	Quality $\uparrow$	FER $\downarrow$	Turns $\downarrow$	Utility $\uparrow$
RO-PnR (full)	0.72	0.66	0.77	0.72	0.06	3.56	0.71
(a) Reward-horizon ablation
immediate next-gain only	0.62	0.54	0.65	0.60	0.12	2.00	0.60
(b) Probe-cost ( $c$ ) sweep
probe cost $=0.00$	0.50	0.46	0.57	0.51	0.11	5.83	0.51
probe cost $=0.03$	0.71	0.65	0.77	0.71	0.08	3.00	0.70

Table 4: Ablation study results, averaged over all (health literacy

\times

belief commitment) user profiles. RO-PnR (full) is our complete method with forward-looking long-horizon reward, probe cost

c=0.01

, and cross-threshold bonus. (a) replaces the forward-looking reward with the immediate next-turn gain; (b) sweeps the per-turn probe cost

c

Appendix figures & tables19 assets

Supplementary material from the paper’s appendix.

Appendix

Figure 3: 3

\times

3 latent user profile grid used in our simulation environment. Users are characterized along two dimensions: health literacy ( Functional , Interactive , Critical ) and belief commitment ( Open , Hesitant , Strong believer ). Each cell defines one latent user type and includes an illustrative response style showing how the user may express concern, interpret evidence, and respond to counterspeech. This profile grid is used to simulate heterogeneous user behavior during multi-turn interaction.

Stage	LR	Epochs	Batch	Grad. accum.	Max len.	Other settings
SFT	$5\times 10^{-5}$	4	1	8	2048	LoRA $r=16$ , $\alpha=32$ , dropout $0.05$ ; bf16; 100 warmup steps; seed 42
Offline GRPO	$5\times 10^{-6}$	2	1	8	2048	$\beta_{\mathrm{KL}}=0.05$ ; SFT CE weight $0.2$ ; warmup ratio $0.03$ ; max grad norm $1.0$ ; seed 42

Appendix

Table 5: Hyperparameters for SFT and GRPO configuration

Score	Persona Accuracy	Persona Consistency
1	The simulated user clearly does not match the assigned health literacy or belief commitment.	The user frequently contradicts the assigned profile, with abrupt and unjustified shifts in knowledge level or belief strength.
2	The simulated user weakly matches the assigned profile. One dimension may be partially reflected, but the other is missing or incorrect.	The user shows unstable behavior, with multiple unexplained shifts in health literacy or belief commitment.
3	The simulated user partially matches the assigned profile. Both dimensions are somewhat recognizable, but the dialogue is vague, generic, or only weakly aligned.	The user is mostly stable, but there are noticeable inconsistencies or minor contradictions across turns.
4	The simulated user largely matches the assigned health literacy and belief commitment, with only minor imperfections.	The user maintains the assigned profile across most turns, and any change in belief strength is mostly justified by the conversation.
5	The simulated user strongly matches the assigned profile. Health literacy and belief commitment are both clearly and accurately expressed.	The user consistently maintains the assigned health literacy and belief commitment throughout the dialogue, with any change being natural and well-supported by the interaction.

Appendix

Table 6: Human evaluation rubric for assessing user simulation quality.

Metric	Persona Accuracy	Persona Consistency
Mean Pairwise Agreement	0.83	0.85
Mean Pairwise Scott’s $\pi$	0.70	0.68
All-Three Agreement	0.74	0.78
Multi-Rater Scott’s $\pi$	0.70	0.68

Appendix

Table 7: Inter-annotator agreement among three evaluators on persona accuracy and persona consistency . Both pairwise and multi-rater statistics indicate substantial agreement.

Metric	Score 1	Score 2	Score 3	Score 4	Score 5	Mean
Persona Accuracy	0%	3%	21%	62%	14%	3.87
Persona Consistency	0%	0%	3%	30%	67%	4.64

Appendix

Table 8: Distribution of human ratings for persona accuracy and persona consistency.

Dimension	Scott’s $\pi$	Mean Pairwise Agreement	All-three Exact Agreement
Audience Alignment	0.76	84.70%	78.00%
Personalized Grounding	0.63	76.00%	65.00%
Tailored Actionability	0.77	88.70%	83.00%
Quality	0.78	86.70%	81.00%

Appendix

Table 9: Human inter-annotator agreement under 0.5-point discretization.

Dim	Scott’s $\pi$	Percent Agreement	MAE	Bias	Within $\pm 0.5$	Within $\pm 1.0$
Audience Alignment	0.51	69.00%	0.29	-0.14	86.00%	94.00%
Personalized Grounding	0.31	51.00%	0.28	-0.14	85.00%	96.00%
Tailored Actionability	0.48	72.00%	0.14	-0.07	95.00%	99.00%
Quality	0.55	73.00%	0.23	-0.11	87.00%	97.00%

Appendix

Table 10: Agreement between the human consensus and the LLM judge across rubric dimensions and the aggregated final score. Bias is computed as consensus minus LLM score.

Dimension	Pearson	Spearman	LLM Mean	Human Mean
Audience Alignment	0.50	0.66	3.76	3.62
Personalized Grounding	0.51	0.67	3.50	3.37
Tailored Actionability	0.72	0.81	3.93	3.86
Quality	0.57	0.72	3.73	3.62

Appendix

Table 11: Correlation between the LLM judge and human consensus under 0.5-point discretization.

Item	Question	Rating
B	How accurate do you think this claim is?	0 = Definitely false / 10 = Definitely true
C	How certain are you about your answer above?	0 = Not at all / 10 = Completely
O	If you saw credible evidence against your view on this claim, how willing would you be to change your mind?	0 = Not at all willing / 10 = Completely willing

Appendix

Table 12: Belief Commitment Determinants. B denotes belief, C denotes certainty, and O denotes openness to change.

User	Total FCCHL Mean	HL Category	Overall $BC_{\text{total}}$	BC Category
User 1	2.07	Communicative	2.03	Hesitant
User 2	1.93	Functional	6.83	Strong
User 3	2.71	Communicative	1.20	Open
User 4	3.00	Critical	1.20	Open
User 5	4.00	Critical	0.40	Open
User 6	3.64	Critical	0.35	Open

Appendix

Table 13: Health Literacy and Belief Commitment Categories. HL categories are mapped from the Total FCCHL mean: 1.00-1.99 = Functional, 2.00- 2.99 = Communicative, and 3.00-4.00 = Critical. BC categories are mapped from

BC_{\text{total}}

BC_{\text{total}}<1.5

= Open,

1.5\leq BC_{\text{total}}<5

= Hesitant, and

BC_{\text{total}}\geq 5

= Strong.

Figure 4: Human pairwise preference comparison between RO-PnR and Fixed-Q across different users. Detailed users’ background are provided in Table 13 .

Figure 5: Questionnaire for health literacy screen

Panel of Figure 6 — Figure 6: System prompt and user prompt for realistic health misinformation persona simulation.

Panel of Figure 7 — Figure 7: Prompt for evaluating the Factual Error.

Panel of Figure 8 — Figure 8: Evaluation rubric for Audience Alignment, Personalized Grounding, and Tailored Actionability.

Panel of Figure 9 — Figure 9: System prompt for the Reactive baseline.

Panel of Figure 10 — Figure 10: Prompt for the Reactive baseline.

Panel of Figure 11 — Figure 11: System prompt for the Confidence baseline.

Panel of Figure 12 — Figure 12: Prompt for the Confidence baseline.

LLM Decision-Making

LLM decision-making studies how language models choose, act, seek information, and allocate resources under goals, uncertainty, constraints, and social pressures.

See all 242 papers

Better with Experience: Self-Evolving LLM Agents for Evidence-Grounded Health Community Notes
Jun 1, 2026Zihang Fu, Fanxiao Li, Jianyang Gu +5Healthcare LLM Agent Self-Improvement
National University of Singapore · Yunnan University · The Ohio State University +1
PCQC: Privileged Counterfactual Question Credit for Multi-Turn Medical Dialogue
Sep 23, 2026Chenxuan Li, Jiayi Wan, Xinrong Chen +3Clinical Reasoning Medical LLMs
Peking University, Beijing, China · Department of Medical Bioinformatics, School of Basic Medical Sciences, Peking University, Beijing, China
A misinformation playbook sharpens judgement without breeding cynicism
Oct 15, 2026Tong Guo, Teng Ye, Yutong Xie +1Fake News Detection
School of Information and Department of Electrical Engineering and Computer Science, University of Michigan

Jun 1, 2026J/K move · Enter open · S save

Better with Experience: Self-Evolving LLM Agents for Evidence-Grounded Health Community Notes

Zihang Fu, Fanxiao Li, Jianyang Gu, Haonan Wang+4

National University of Singapore · Yunnan University · The Ohio State University+1

Healthcare LLM Agent Self-Improvement Automated Fact-Checking Text Generation Memory-Augmented Language Model Agents

Open paper AskPDF arXiv

Large Language Model (LLM)-augmented Community Notes offer a scalable path for timely, evidence-grounded correction of health misinformation on social platforms. However, they still reset at every post, leaving useful correction experience from prior cases unused. We introduce EvoNote, an agentic framework that enables health Community Notes generation to self-evolve through an evolving experience memory of prior misinformation correction episodes. Its core is fine-grained credit assignment: EvoNote grounds trajectory-level feedback in health-specific note qualities and distills it into action-level memory for claim analysis, evidence acquisition, and note writing. We evaluate EvoNote on MM-HealthCN, a 1.2K-instance multimodal benchmark of user-flagged health posts with human-written Community Notes and crowd-derived helpfulness labels. Under a human-validated hierarchical utility judge, EvoNote-generated notes are preferred over corresponding human-written notes in 89.6% of cases; on a separate set of Needs More Ratings posts without a crowd helpfulness verdict, EvoNote produces helpful notes for 82.0% of cases. It also reduces time to an available candidate correction from multi-hour post-to-note delays to under 2 minutes on average. Analyses link these quality gains to stronger evidence use and reusable correction strategies, positioning self-evolving note generation as a promising paradigm for scalable health misinformation governance.

Abstract

LLM Decision-Making

Explore similar work

Better with Experience: Self-Evolving LLM Agents for Evidence-Grounded Health Community Notes

PCQC: Privileged Counterfactual Question Credit for Multi-Turn Medical Dialogue

A misinformation playbook sharpens judgement without breeding cynicism