- Rating
- 2
- Confidence
- 4
- Informativeness
- 1
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
The framework uses social hypergraphs to identify risky groups, generate evidence-grounded corrections, and coordinate messages for users belonging to overlapping groups. Group Doubt Ratio and Correction History inform later user updates. Experiments cover four misinformation datasets in a seven-day LLM-agent simulation, with baseline comparisons, component and structural ablations, persistence tests, and a smaller intervention model.
Critical strengths
- Explicit group membership lets the intervention agent adapt corrections to local discourse and fuse messages for users shared across overlapping or nested groups.
- Across 400 news items, the method obtains the lowest final simulated misinformation trust on all four datasets. The propagation analysis distinguishes supportive sharing from doubt or corrective sharing.
Critical weaknesses
- The no-hypergraph control changes both propagation and intervention: it removes group-based routing and replaces adaptive corrections with one neutral fact-check (Section 4.4.1). The performance gap therefore cannot be attributed specifically to higher-order relations. The operations removed by the separate w/o HR ablation are insufficiently specified, while Appendix B reports projected full-set values rather than direct measurements for its structural controls.
- Correction History is supplied to simulated users as historical corrective context during subsequent judgment updates (Section 3.4). Removing it changes both access to response-outcome summaries and access to additional corrective context. The ablation does not distinguish these effects. The persistence test retains both Individual Memory and Correction History, and, as Appendix E.4 acknowledges, establishes only their joint effect.
Questions for authors
- What exactly is removed in w/o HR? Can the authors isolate the structural contribution while retaining the same exposure routing, factual evidence, message budget, and group adaptation, and report directly measured results for the matched subset used in Appendix B?
- Does Correction History outperform a matched-length context containing the earlier corrections without response-outcome summaries? This would distinguish the contribution of social feedback from simply retaining more corrective information.
12 comments
Response to reviewer#af5N (Part-2)
Concern 2: Appendix B reports projected full-set values rather than direct measurements for its structural controls.
Thank you for pointing our this issue. Appendix B examines the contributions of homophily-based membership and group-adaptive intervention through two structural controls: Random Membership and Flat Intervention. Due to the high simulation cost (~1 hour per news item), we initially evaluated these controls on matched subsets and projected their full-set results using relative changes. Following your suggestion, we add a full-dataset experiment on all 400 misinformation items under identical settings. The results show that Ours (main results in Table 1) still have the lowest Trust_D7 (0.2380), reducing it by 17.1% and 27.5% compared with Random Membership and Flat. Detailed results are as follows:
| Dataset | Metric | Ours | Rand.Member. | Flat |
|---|---|---|---|---|
| Arg-En | Trust_D7 | 0.2683 | 0.3497 | 0.3909 |
| Arg-En | SpreadRate_D7 | 0.0696 | 0.0737 | 0.0255 |
| Snopes | Trust_D7 | 0.2678 | 0.3466 | 0.3805 |
| Snopes | SpreadRate_D7 | 0.0623 | 0.0312 | 0.0194 |
| CoAID | Trust_D7 | 0.1963 | 0.2272 | 0.2638 |
| CoAID | SpreadRate_D7 | 0.2089 | 0.2978 | 0.1871 |
| ECTF | Trust_D7 | 0.2195 | 0.2255 | 0.2783 |
| ECTF | SpreadRate_D7 | 0.0748 | 0.1130 | 0.0597 |
| Overall | Trust_D7 | 0.2380 | 0.2872 | 0.3283 |
| Overall | SpreadRate_D7 | 0.1039 | 0.1289 | 0.0729 |
We will replace the projected table in Appendix B with these measurements and revise the corresponding interpretation.
Response to reviewer#af5N (Part-3)
Concern 3: Correction History is supplied to simulated users as historical corrective context during subsequent judgment updates (Section 3.4). Removing it changes both access to response-outcome summaries and access to additional corrective context. The ablation does not distinguish these effects.
Thank you for this valuable suggestion. We interpret the reviewer's additional corrective context and response-outcome summaries as the two components of Correction History (CH): Corrective Context (Part I) and Social Response (Part II), respectively. To further distinguish the contributions of corrective context and social response in Correction History (CH), we clarify its two components and conduct two complementary ablation experiments. Details are as follows:
(1) What Are the Two Components within Correction History?
- Corrective Context (Part I): A summary of delivered corrections, successful/failed strategies, and recommended adjustments.
- Social Response (Part II): A summary of pre-/post-intervention changes in comments, stances, and actions.
We will revise Section 3.4 to explicitly clarify these two components.
(2) How Do We Isolate Their Respective Contributions?
Following your suggestion, we add two ablations (w/o Part I and w/o Part II) to separately evaluate the contributions of corrective context and social response.
Experimental Setup
- Data: All 400 misinformation from four datasets.
- Method: Four Correction History (CH) ablations: Ours (full CH), w/o CH (remove both parts), w/o Part I (retain only Part II), and w/o Part II (retain only Part I).
- Protocol: Follow the same 7-day simulation settings as the main experiments, varying only the retained CH components. The retained contexts in w/o Part I and w/o Part II are length-matched to full CH through controlled padding.
The results are reported below:
| Dataset | Metric | Ours | w/o CH | w/o PartI | w/o PartII |
|---|---|---|---|---|---|
| Arg-En | Trust_D7 | 0.2683 | 0.2726 | 0.3550 | 0.3773 |
| Arg-En | SpreadRate_D7 | 0.0696 | 0.3467 | 0.3138 | 0.2886 |
| Snopes | Trust_D7 | 0.2678 | 0.2762 | 0.3850 | 0.3477 |
| Snopes | SpreadRate_D7 | 0.0623 | 0.0679 | 0.1524 | 0.0883 |
| CoAID | Trust_D7 | 0.1963 | 0.2271 | 0.2258 | 0.2806 |
| CoAID | SpreadRate_D7 | 0.2089 | 0.2958 | 0.3816 | 0.4722 |
| ECTF | Trust_D7 | 0.2195 | 0.2306 | 0.2353 | 0.1793 |
| ECTF | SpreadRate_D7 | 0.0748 | 0.1981 | 0.1594 | 0.2974 |
Results and Interpretation: Full CH achieves the lowest SpreadRate_D7 across all four datasets and the lowest Trust_D7 on three datasets. These results validate the individual contributions of Corrective Context and Social Response, supporting the benefit of social feedback.
Response to reviewer#af5N (Part-1)
In our framework, higher-order relations (nested/overlapping hyperedges) enable Cross-Hyperedge Propagation. However, No-Hypergraph Control does not isolate these relations; instead, it merges all users into a single global group and replaces Relation-Aware Intervention Coordination with a neutral fact-check, thereby changing both propagation and intervention.
Existing evaluation: Our existing Case A (w/o HR) preserves the original hypergraph and Cross-Hyperedge Propagation but removes cross-hyperedge intervention coordination by randomly selecting one hyperedge's intervention for users in nested/overlapping regions.
Complementary experiments:: Following your suggestion, we further introduce Case B to isolate the contribution of higher-order structural relations. It removes nested/overlapping relations to eliminate Cross-Hyperedge Propagation, while retaining users in all their originally affiliated hyperedges to preserve Relation-Aware Intervention Coordination.
Details are as follows:
(1) Case A: Removing Relation-Aware Intervention Coordination (Existing Ablation)
(2) Case B: Removing Higher-Order Structural Relations (Additional Ablation)
The results are reported below:
Results and Interpretation: On average, Ours achieves lower Trust_D7 and SpreadRate_D7 than both Case A and B across the four datasets. These results support the contributions of Relation-Aware Intervention Coordination and higher-order structural relations to reducing misinformation belief and spread.
We will present their separate operations and measurement units in §4.3–4.4, together with the corresponding factual-input and correction-budget specification.