高级检索

    虚假信息传播后认知影响的图干预消解

    Graph Intervention for Mitigating Cognitive Impact after Misinformation Propagation

    • 摘要: 在社交网络信息治理中,平台还需面对虚假信息已经传播并形成群体反应后的处置问题。本文将该场景形式化为可观测传播图上的认知影响消解任务,提出结构层与决策层解耦的图干预智能体框架。结构层负责传播图建模、节点状态估计、群体候选构造和规范回放;决策层由大语言模型智能体在受控工具空间内完成候选比较、消息审计和最终动作提交。在CED、PHEME、Weibo21和MisBot共13 660个传播样本、3种模型上的主实验中,各方法在给定传播图快照、共同的逐样本预算上限和规范回放协议下进行比较,本方法的平均simCHR高于主实验所列对照;相对一次生成基线,12个数据集—模型组合的配对差值均为正。补充实验表明,群体候选空间与状态感知评分是规范回放收益的重要来源;固定目标集合时,智能体纠偏文本获得的专家预期误信下降评分高于通用模板。实验结果表明,图干预智能体在传播后群体干预模拟中取得了正向的代理减害收益。

       

      Abstract: Misinformation governance must also address cases in which false narratives have already spread and elicited heterogeneous group responses. We formulate this setting as cognitive-impact mitigation on observable propagation graphs and propose a graph intervention agent with decoupled structural and decision layers. The structural layer models propagation graphs, estimates node states, constructs group candidates, and performs standardized simulation replay. The decision layer uses a large language model agent to compare candidates, audit corrective messages, and submit actions within a controlled tool space. Experiments cover 13660 propagation samples from CED, PHEME, Weibo21, and MisBot with three language models. In the main experiments, methods are compared on given propagation-graph snapshots under common per-sample budget caps and a unified simulation replay protocol. The proposed method achieves a higher mean simCHR than the controls reported in these experiments, and its paired improvement over the one-shot baseline is positive in all 12 dataset–model combinations. Additional analyses show that the group candidate space and state-aware scoring are major sources of replay gain. With intervention targets fixed, agent-generated corrective messages receive higher expert-rated expected belief-reduction scores than generic templates. These results show that the proposed agent achieves positive proxy harm-mitigation gains in simulated post-propagation group intervention.

       

    /

    返回文章
    返回